🎭🎉 Cognitive Crescendos 🎹💃 & Neural Harmonies 🎸🎤

🔎 How can Self Rewarding AI be used in streamlit python and html5 with javascript to create a context prompt and document and search retrieval?
...

Here is an example of the code I am currently working with:

import streamlit as st
import self_rewarding_ai as sra

Create a context prompt

context_prompt = st.text_input("Enter a context prompt:")

Use Self Rewarding AI to generate documents

documents = sra.generate_documents(context_prompt)

Display the documents using streamlit-aggrid

st.ag_grid(documents)

Use Self Rewarding AI to perform a search

search_query = st.text_input("Enter a search query:")
search_results = sra.search(search_query, documents)

Display the search results using streamlit-aggrid

st.ag_grid(search_results)

...

🩺🔍 Search Results
09 Oct 2023 | SALMON: Self-Alignment with Principle-Following Reward Models | ⬇️
Zhiqing Sun, Yikang Shen, Hongxin Zhang, Qinhong Zhou, Zhenfang Chen, David Cox, Yiming Yang, Chuang Gan

Supervised Fine-Tuning (SFT) on response demonstrations combined with Reinforcement Learning from Human Feedback (RLHF) constitutes a powerful paradigm for aligning LLM-based AI agents. However, a significant limitation of such an approach is its dependency on high-quality human annotations, making its application to intricate tasks challenging due to difficulties in obtaining consistent response demonstrations and in-distribution response preferences. This paper presents a novel approach, namely SALMON (Self-ALignMent with principle-fOllowiNg reward models), to align base language models with minimal human supervision, using only a small set of human-defined principles, yet achieving superior performance. Central to our approach is a principle-following reward model. Trained on synthetic preference data, this model can generate reward scores based on arbitrary human-defined principles. By merely adjusting these principles during the RL training phase, we gain full control over the preferences with the reward model, subsequently influencing the behavior of the RL-trained policies, and eliminating the reliance on the collection of online human preferences. Applying our method to the LLaMA-2-70b base language model, we developed an AI assistant named Dromedary-2. With only 6 exemplars for in-context learning and 31 human-defined principles, Dromedary-2 significantly surpasses the performance of several state-of-the-art AI systems, including LLaMA-2-Chat-70b, on various benchmark datasets. We have open-sourced the code and model weights to encourage further research into aligning LLM-based AI agents with enhanced supervision efficiency, improved controllability, and scalable oversight.

18 Feb 2024 | MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization | ⬇️
Yasaman Jafari, Dheeraj Mekala, Rose Yu, Taylor Berg-Kirkpatrick

RL-based techniques can be used to search for prompts that when fed into a target language model maximize a set of user-specified reward functions. However, in many target applications, the natural reward functions are in tension with one another -- for example, content preservation vs. style matching in style transfer tasks. Current techniques focus on maximizing the average of reward functions, which does not necessarily lead to prompts that achieve balance across rewards -- an issue that has been well-studied in the multi-objective and robust optimization literature. In this paper, we adapt several techniques for multi-objective optimization to RL-based discrete prompt optimization -- two that consider volume of the Pareto reward surface, and another that chooses an update direction that benefits all rewards simultaneously. We conduct an empirical analysis of these methods on two NLP tasks: style transfer and machine translation, each using three competing reward functions. Our experiments demonstrate that multi-objective methods that directly optimize volume perform better and achieve a better balance of all rewards than those that attempt to find monotonic update directions.

19 Mar 2023 | CLIP4MC: An RL-Friendly Vision-Language Model for Minecraft | ⬇️
Ziluo Ding, Hao Luo, Ke Li, Junpeng Yue, Tiejun Huang, and Zongqing Lu

One of the essential missions in the AI research community is to build an autonomous embodied agent that can attain high-level performance across a wide spectrum of tasks. However, acquiring reward/penalty in all open-ended tasks is unrealistic, making the Reinforcement Learning (RL) training procedure impossible. In this paper, we propose a novel cross-modal contrastive learning framework architecture, CLIP4MC, aiming to learn an RL-friendly vision-language model that serves as a reward function for open-ended tasks. Therefore, no further task-specific reward design is needed. Intuitively, it is more reasonable for the model to address the similarity between the video snippet and the language prompt at both the action and entity levels. To this end, a motion encoder is proposed to capture the motion embeddings across different intervals. The correlation scores are then used to construct the auxiliary reward signal for RL agents. Moreover, we construct a neat YouTube dataset based on the large-scale YouTube database provided by MineDojo. Specifically, two rounds of filtering operations guarantee that the dataset covers enough essential information and that the video-text pair is highly correlated. Empirically, we show that the proposed method achieves better performance on RL tasks compared with baselines.

14 Dec 2023 | Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft | ⬇️
Hao Li, Xue Yang, Zhaokai Wang, Xizhou Zhu, Jie Zhou, Yu Qiao, Xiaogang Wang, Hongsheng Li, Lewei Lu, Jifeng Dai

Traditional reinforcement-learning-based agents rely on sparse rewards that often only use binary values to indicate task completion or failure. The challenge in exploration efficiency makes it difficult to effectively learn complex tasks in Minecraft. To address this, this paper introduces an advanced learning system, named Auto MC-Reward, that leverages Large Language Models (LLMs) to automatically design dense reward functions, thereby enhancing the learning efficiency. Auto MC-Reward consists of three important components: Reward Designer, Reward Critic, and Trajectory Analyzer. Given the environment information and task descriptions, the Reward Designer first design the reward function by coding an executable Python function with predefined observation inputs. Then, our Reward Critic will be responsible for verifying the code, checking whether the code is self-consistent and free of syntax and semantic errors. Further, the Trajectory Analyzer summarizes possible failure causes and provides refinement suggestions according to collected trajectories. In the next round, Reward Designer will take further refine and iterate the dense reward function based on feedback. Experiments demonstrate a significant improvement in the success rate and learning efficiency of our agents in complex tasks in Minecraft, such as obtaining diamond with the efficient ability to avoid lava, and efficiently explore trees and animals that are sparse on the plains biome.

23 Jan 2023 | Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP | ⬇️
Omar Khattab, Keshav Santhanam, Xiang Lisa Li, David Hall, Percy Liang, Christopher Potts, Matei Zaharia

Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM). Existing work has combined these in simple "retrieve-then-read" pipelines in which the RM retrieves passages that are inserted into the LM prompt. To begin to fully realize the potential of frozen LMs and RMs, we propose Demonstrate-Search-Predict (DSP), a framework that relies on passing natural language texts in sophisticated pipelines between an LM and an RM. DSP can express high-level programs that bootstrap pipeline-aware demonstrations, search for relevant passages, and generate grounded predictions, systematically breaking down problems into small transformations that the LM and RM can handle more reliably. We have written novel DSP programs for answering questions in open-domain, multi-hop, and conversational settings, establishing in early evaluations new state-of-the-art in-context learning results and delivering 37-120%, 8-39%, and 80-290% relative gains against the vanilla LM (GPT-3.5), a standard retrieve-then-read pipeline, and a contemporaneous self-ask pipeline, respectively. We release DSP at https://github.com/stanfordnlp/dsp

15 Feb 2024 | Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community | ⬇️
Arman Isajanyan, Artur Shatveryan, David Kocharyan, Zhangyang Wang, Humphrey Shi

Social reward as a form of community recognition provides a strong source of motivation for users of online platforms to engage and contribute with content. The recent progress of text-conditioned image synthesis has ushered in a collaborative era where AI empowers users to craft original visual artworks seeking community validation. Nevertheless, assessing these models in the context of collective community preference introduces distinct challenges. Existing evaluation methods predominantly center on limited size user studies guided by image quality and prompt alignment. This work pioneers a paradigm shift, unveiling Social Reward - an innovative reward modeling framework that leverages implicit feedback from social network users engaged in creative editing of generated images. We embark on an extensive journey of dataset curation and refinement, drawing from Picsart: an online visual creation and editing platform, yielding a first million-user-scale dataset of implicit human preferences for user-generated visual art named Picsart Image-Social. Our analysis exposes the shortcomings of current metrics in modeling community creative preference of text-to-image models' outputs, compelling us to introduce a novel predictive model explicitly tailored to address these limitations. Rigorous quantitative experiments and user study show that our Social Reward model aligns better with social popularity than existing metrics. Furthermore, we utilize Social Reward to fine-tune text-to-image models, yielding images that are more favored by not only Social Reward, but also other established metrics. These findings highlight the relevance and effectiveness of Social Reward in assessing community appreciation for AI-generated artworks, establishing a closer alignment with users' creative goals: creating popular visual art. Codes can be accessed at https://github.com/Picsart-AI-Research/Social-Reward

08 Feb 2024 | Self-Rewarding Language Models | ⬇️
Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, Jason Weston

We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal. Current approaches commonly train reward models from human preferences, which may then be bottlenecked by human performance level, and secondly these separate frozen reward models cannot then learn to improve during LLM training. In this work, we study Self-Rewarding Language Models, where the language model itself is used via LLM-as-a-Judge prompting to provide its own rewards during training. We show that during Iterative DPO training that not only does instruction following ability improve, but also the ability to provide high-quality rewards to itself. Fine-tuning Llama 2 70B on three iterations of our approach yields a model that outperforms many existing systems on the AlpacaEval 2.0 leaderboard, including Claude 2, Gemini Pro, and GPT-4 0613. While there is much left still to explore, this work opens the door to the possibility of models that can continually improve in both axes.

26 May 2022 | Learning Dense Reward with Temporal Variant Self-Supervision | ⬇️
Yuning Wu, Jieliang Luo, Hui Li

Rewards play an essential role in reinforcement learning. In contrast to rule-based game environments with well-defined reward functions, complex real-world robotic applications, such as contact-rich manipulation, lack explicit and informative descriptions that can directly be used as a reward. Previous effort has shown that it is possible to algorithmically extract dense rewards directly from multimodal observations. In this paper, we aim to extend this effort by proposing a more efficient and robust way of sampling and learning. In particular, our sampling approach utilizes temporal variance to simulate the fluctuating state and action distribution of a manipulation task. We then proposed a network architecture for self-supervised learning to better incorporate temporal information in latent representations. We tested our approach in two experimental setups, namely joint-assembly and door-opening. Preliminary results show that our approach is effective and efficient in learning dense rewards, and the learned rewards lead to faster convergence than baselines.

06 Dec 2018 | Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization | ⬇️
Alexandre Laterre and Yunguan Fu and Mohamed Khalil Jabri and Alain-Sam Cohen and David Kas and Karl Hajjar and Torbjorn S. Dahl and Amine Kerkeni and Karim Beguir

Adversarial self-play in two-player games has delivered impressive results when used with reinforcement learning algorithms that combine deep neural networks and tree search. Algorithms like AlphaZero and Expert Iteration learn tabula-rasa, producing highly informative training data on the fly. However, the self-play training strategy is not directly applicable to single-player games. Recently, several practically important combinatorial optimisation problems, such as the travelling salesman problem and the bin packing problem, have been reformulated as reinforcement learning problems, increasing the importance of enabling the benefits of self-play beyond two-player games. We present the Ranked Reward (R2) algorithm which accomplishes this by ranking the rewards obtained by a single agent over multiple games to create a relative performance metric. Results from applying the R2 algorithm to instances of a two-dimensional and three-dimensional bin packing problems show that it outperforms generic Monte Carlo tree search, heuristic algorithms and integer programming solvers. We also present an analysis of the ranked reward mechanism, in particular, the effects of problem instances with varying difficulty and different ranking thresholds.

17 Sep 2021 | Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration | ⬇️
Oliver Groth, Markus Wulfmeier, Giulia Vezzani, Vibhavari Dasagi, Tim Hertweck, Roland Hafner, Nicolas Heess, Martin Riedmiller

Curiosity-based reward schemes can present powerful exploration mechanisms which facilitate the discovery of solutions for complex, sparse or long-horizon tasks. However, as the agent learns to reach previously unexplored spaces and the objective adapts to reward new areas, many behaviours emerge only to disappear due to being overwritten by the constantly shifting objective. We argue that merely using curiosity for fast environment exploration or as a bonus reward for a specific task does not harness the full potential of this technique and misses useful skills. Instead, we propose to shift the focus towards retaining the behaviours which emerge during curiosity-based learning. We posit that these self-discovered behaviours serve as valuable skills in an agent's repertoire to solve related tasks. Our experiments demonstrate the continuous shift in behaviour throughout training and the benefits of a simple policy snapshot method to reuse discovered behaviour for transfer tasks.

21 Oct 2023 | Learning Reward for Physical Skills using Large Language Model | ⬇️
Yuwei Zeng, Yiqing Xu

Learning reward functions for physical skills are challenging due to the vast spectrum of skills, the high-dimensionality of state and action space, and nuanced sensory feedback. The complexity of these tasks makes acquiring expert demonstration data both costly and time-consuming. Large Language Models (LLMs) contain valuable task-related knowledge that can aid in learning these reward functions. However, the direct application of LLMs for proposing reward functions has its limitations such as numerical instability and inability to incorporate the environment feedback. We aim to extract task knowledge from LLMs using environment feedback to create efficient reward functions for physical skills. Our approach consists of two components. We first use the LLM to propose features and parameterization of the reward function. Next, we update the parameters of this proposed reward function through an iterative self-alignment process. In particular, this process minimizes the ranking inconsistency between the LLM and our learned reward functions based on the new observations. We validated our method by testing it on three simulated physical skill learning tasks, demonstrating effective support for our design choices.

10 Apr 2023 | Exploring Effective Factors for Improving Visual In-Context Learning | ⬇️
Yanpeng Sun, Qiang Chen, Jian Wang, Jingdong Wang, Zechao Li

The In-Context Learning (ICL) is to understand a new task via a few demonstrations (aka. prompt) and predict new inputs without tuning the models. While it has been widely studied in NLP, it is still a relatively new area of research in computer vision. To reveal the factors influencing the performance of visual in-context learning, this paper shows that prompt selection and prompt fusion are two major factors that have a direct impact on the inference performance of visual context learning. Prompt selection is the process of identifying the most appropriate prompt or example to help the model understand new tasks. This is important because providing the model with relevant prompts can help it learn more effectively and efficiently. Prompt fusion involves combining knowledge from different positions within the large-scale visual model. By doing this, the model can leverage the diverse knowledge stored in different parts of the model to improve its performance on new tasks. Based these findings, we propose a simple framework prompt-SelF for visual in-context learning. Specifically, we first use the pixel-level retrieval method to select a suitable prompt, and then use different prompt fusion methods to activate all the knowledge stored in the large-scale model, and finally ensemble the prediction results obtained from different prompt fusion methods to obtain the final prediction results. And we conduct extensive experiments on single-object segmentation and detection tasks to demonstrate the effectiveness of prompt-SelF. Remarkably, the prompt-SelF has outperformed OSLSM based meta-learning in 1-shot segmentation for the first time. This indicated the great potential of visual in-context learning. The source code and models will be available at \url{https://github.com/syp2ysy/prompt-SelF}.

01 Dec 2022 | A General Purpose Supervisory Signal for Embodied Agents | ⬇️
Kunal Pratap Singh, Jordi Salvador, Luca Weihs, Aniruddha Kembhavi

Training effective embodied AI agents often involves manual reward engineering, expert imitation, specialized components such as maps, or leveraging additional sensors for depth and localization. Another approach is to use neural architectures alongside self-supervised objectives which encourage better representation learning. In practice, there are few guarantees that these self-supervised objectives encode task-relevant information. We propose the Scene Graph Contrastive (SGC) loss, which uses scene graphs as general-purpose, training-only, supervisory signals. The SGC loss does away with explicit graph decoding and instead uses contrastive learning to align an agent's representation with a rich graphical encoding of its environment. The SGC loss is generally applicable, simple to implement, and encourages representations that encode objects' semantics, relationships, and history. Using the SGC loss, we attain significant gains on three embodied tasks: Object Navigation, Multi-Object Navigation, and Arm Point Navigation. Finally, we present studies and analyses which demonstrate the ability of our trained representation to encode semantic cues about the environment.

14 Dec 2023 | ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF | ⬇️
Victor Gallego

In this work, we address the problem of directing the text generation of a language model (LM) towards a desired behavior, aligning the generated text with the preferences of the human operator. We propose using another, instruction-tuned language model as a critic reward model in a zero-shot way thanks to the prompt of a Yes-No question that represents the user preferences, without requiring further labeled data. This zero-shot reward model provides the learning signal to further fine-tune the base LM using Reinforcement Learning from AI Feedback (RLAIF); yet our approach is also compatible in other contexts such as quality-diversity search. Extensive evidence of the capabilities of the proposed ZYN framework is provided through experiments in different domains related to text generation, including detoxification; optimizing sentiment of movie reviews, or any other attribute; steering the opinion about a particular topic the model may have; and personalizing prompt generators for text-to-image tasks. Code available at \url{https://github.com/vicgalle/zero-shot-reward-models/}.

27 Feb 2023 | Reward Design with Language Models | ⬇️
Minae Kwon, Sang Michael Xie, Kalesha Bullard, Dorsa Sadigh

Reward design in reinforcement learning (RL) is challenging since specifying human notions of desired behavior may be difficult via reward functions or require many expert demonstrations. Can we instead cheaply design rewards using a natural language interface? This paper explores how to simplify reward design by prompting a large language model (LLM) such as GPT-3 as a proxy reward function, where the user provides a textual prompt containing a few examples (few-shot) or a description (zero-shot) of the desired behavior. Our approach leverages this proxy reward function in an RL framework. Specifically, users specify a prompt once at the beginning of training. During training, the LLM evaluates an RL agent's behavior against the desired behavior described by the prompt and outputs a corresponding reward signal. The RL agent then uses this reward to update its behavior. We evaluate whether our approach can train agents aligned with user objectives in the Ultimatum Game, matrix games, and the DealOrNoDeal negotiation task. In all three tasks, we show that RL agents trained with our framework are well-aligned with the user's objectives and outperform RL agents trained with reward functions learned via supervised learning

07 Mar 2023 | VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training | ⬇️
Yecheng Jason Ma, Shagun Sodhani, Dinesh Jayaraman, Osbert Bastani, Vikash Kumar, Amy Zhang

Reward and representation learning are two long-standing challenges for learning an expanding set of robot manipulation skills from sensory observations. Given the inherent cost and scarcity of in-domain, task-specific robot data, learning from large, diverse, offline human videos has emerged as a promising path towards acquiring a generally useful visual representation for control; however, how these human videos can be used for general-purpose reward learning remains an open question. We introduce
V
Value-
I
Implicit
P
Pre-training (VIP), a self-supervised pre-trained visual representation capable of generating dense and smooth reward functions for unseen robotic tasks. VIP casts representation learning from human videos as an offline goal-conditioned reinforcement learning problem and derives a self-supervised dual goal-conditioned value-function objective that does not depend on actions, enabling pre-training on unlabeled human videos. Theoretically, VIP can be understood as a novel implicit time contrastive objective that generates a temporally smooth embedding, enabling the value function to be implicitly defined via the embedding distance, which can then be used to construct the reward for any goal-image specified downstream task. Trained on large-scale Ego4D human videos and without any fine-tuning on in-domain, task-specific data, VIP's frozen representation can provide dense visual reward for an extensive set of simulated and
real-robot
real-robot tasks, enabling diverse reward-based visual control methods and significantly outperforming all prior pre-trained representations. Notably, VIP can enable simple,
few-shot
few-shot offline RL on a suite of real-world robot tasks with as few as 20 trajectories.

03 Feb 2023 | Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased | ⬇️
Chao Yu, Jiaxuan Gao, Weilin Liu, Botian Xu, Hao Tang, Jiaqi Yang, Yu Wang, Yi Wu

There is a recent trend of applying multi-agent reinforcement learning (MARL) to train an agent that can cooperate with humans in a zero-shot fashion without using any human data. The typical workflow is to first repeatedly run self-play (SP) to build a policy pool and then train the final adaptive policy against this pool. A crucial limitation of this framework is that every policy in the pool is optimized w.r.t. the environment reward function, which implicitly assumes that the testing partners of the adaptive policy will be precisely optimizing the same reward function as well. However, human objectives are often substantially biased according to their own preferences, which can differ greatly from the environment reward. We propose a more general framework, Hidden-Utility Self-Play (HSP), which explicitly models human biases as hidden reward functions in the self-play objective. By approximating the reward space as linear functions, HSP adopts an effective technique to generate an augmented policy pool with biased policies. We evaluate HSP on the Overcooked benchmark. Empirical results show that our HSP method produces higher rewards than baselines when cooperating with learned human models, manually scripted policies, and real humans. The HSP policy is also rated as the most assistive policy based on human feedback.

09 Nov 2020 | Reward Conditioned Neural Movement Primitives for Population Based Variational Policy Optimization | ⬇️
M.Tuluhan Akbulut, Utku Bozdogan, Ahmet Tekden and Emre Ugur

The aim of this paper is to study the reward based policy exploration problem in a supervised learning approach and enable robots to form complex movement trajectories in challenging reward settings and search spaces. For this, the experience of the robot, which can be bootstrapped from demonstrated trajectories, is used to train a novel Neural Processes-based deep network that samples from its latent space and generates the required trajectories given desired rewards. Our framework can generate progressively improved trajectories by sampling them from high reward landscapes, increasing the reward gradually. Variational inference is used to create a stochastic latent space to sample varying trajectories in generating population of trajectories given target rewards. We benefit from Evolutionary Strategies and propose a novel crossover operation, which is applied in the self-organized latent space of the individual policies, allowing blending of the individuals that might address different factors in the reward function. Using a number of tasks that require sequential reaching to multiple points or passing through gaps between objects, we showed that our method provides stable learning progress and significant sample efficiency compared to a number of state-of-the-art robotic reinforcement learning methods. Finally, we show the real-world suitability of our method through real robot execution involving obstacle avoidance.

06 Feb 2024 | Reinforcement Learning from Bagged Reward: A Transformer-based Approach for Instance-Level Reward Redistribution | ⬇️
Yuting Tang and Xin-Qiang Cai and Yao-Xiang Ding and Qiyu Wu and Guoqing Liu and Masashi Sugiyama

In reinforcement Learning (RL), an instant reward signal is generated for each action of the agent, such that the agent learns to maximize the cumulative reward to obtain the optimal policy. However, in many real-world applications, the instant reward signals are not obtainable by the agent. Instead, the learner only obtains rewards at the ends of bags, where a bag is defined as a partial sequence of a complete trajectory. In this situation, the learner has to face the significant difficulty of exploring the unknown instant rewards in the bags, which could not be addressed by existing approaches, including those trajectory-based approaches that consider only complete trajectories and ignore the inner reward distributions. To formally study this situation, we introduce a novel RL setting termed Reinforcement Learning from Bagged Rewards (RLBR), where only the bagged rewards of sequences can be obtained. We provide the theoretical study to establish the connection between RLBR and standard RL in Markov Decision Processes (MDPs). To effectively explore the reward distributions within the bagged rewards, we propose a Transformer-based reward model, the Reward Bag Transformer (RBT), which uses the self-attention mechanism for interpreting the contextual nuances and temporal dependencies within each bag. Extensive experimental analyses demonstrate the superiority of our method, particularly in its ability to mimic the original MDP's reward distribution, highlighting its proficiency in contextual understanding and adaptability to environmental dynamics.

08 Oct 2021 | Explaining Reward Functions to Humans for Better Human-Robot Collaboration | ⬇️
Lindsay Sanneman and Julie Shah

Explainable AI techniques that describe agent reward functions can enhance human-robot collaboration in a variety of settings. One context where human understanding of agent reward functions is particularly beneficial is in the value alignment setting. In the value alignment context, an agent aims to infer a human's reward function through interaction so that it can assist the human with their tasks. If the human can understand where gaps exist in the agent's reward understanding, they will be able to teach more efficiently and effectively, leading to quicker human-agent team performance improvements. In order to support human collaborators in the value alignment setting and similar contexts, it is first important to understand the effectiveness of different reward explanation techniques in a variety of domains. In this paper, we introduce a categorization of information modalities for reward explanation techniques, suggest a suite of assessment techniques for human reward understanding, and introduce four axes of domain complexity. We then propose an experiment to study the relative efficacy of a broad set of reward explanation techniques covering multiple modalities of information in a set of domains of varying complexity.

Date: 09 Oct 2023

Title: SALMON: Self-Alignment with Principle-Following Reward Models

Abstract Link: https://arxiv.org/abs/2310.05910

PDF Link: https://arxiv.org/pdf/2310.05910

Local Abstract: View Abstract

Local PDF: View PDF

Date: 18 Feb 2024

Title: MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization

Abstract Link: https://arxiv.org/abs/2402.11711

PDF Link: https://arxiv.org/pdf/2402.11711

Local Abstract: View Abstract

Local PDF: View PDF

Date: 19 Mar 2023

Title: CLIP4MC: An RL-Friendly Vision-Language Model for Minecraft

Abstract Link: https://arxiv.org/abs/2303.10571

PDF Link: https://arxiv.org/pdf/2303.10571

Local Abstract: View Abstract

Local PDF: View PDF

Date: 14 Dec 2023

Title: Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft

Abstract Link: https://arxiv.org/abs/2312.09238

PDF Link: https://arxiv.org/pdf/2312.09238

Local Abstract: View Abstract

Local PDF: View PDF

Date: 23 Jan 2023

Title: Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP

Abstract Link: https://arxiv.org/abs/2212.14024

PDF Link: https://arxiv.org/pdf/2212.14024

Local Abstract: View Abstract

Local PDF: View PDF

Date: 15 Feb 2024

Title: Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community

Abstract Link: https://arxiv.org/abs/2402.09872

PDF Link: https://arxiv.org/pdf/2402.09872

Local Abstract: View Abstract

Local PDF: View PDF

Date: 08 Feb 2024

Title: Self-Rewarding Language Models

Abstract Link: https://arxiv.org/abs/2401.10020

PDF Link: https://arxiv.org/pdf/2401.10020

Local Abstract: View Abstract

Local PDF: View PDF

Date: 26 May 2022

Title: Learning Dense Reward with Temporal Variant Self-Supervision

Abstract Link: https://arxiv.org/abs/2205.10431

PDF Link: https://arxiv.org/pdf/2205.10431

Local Abstract: View Abstract

Local PDF: View PDF

Date: 06 Dec 2018

Title: Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization

Abstract Link: https://arxiv.org/abs/1807.01672

PDF Link: https://arxiv.org/pdf/1807.01672

Local Abstract: View Abstract

Local PDF: View PDF