Initial commit

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,75 @@
+---
+library_name: stable-baselines3
+tags:
+- BreakoutNoFrameskip-v4
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: QRDQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: BreakoutNoFrameskip-v4
+      type: BreakoutNoFrameskip-v4
+    metrics:
+    - type: mean_reward
+      value: 2.30 +/- 3.07
+      name: mean_reward
+      verified: false
+---
+
+# **QRDQN** Agent playing **BreakoutNoFrameskip-v4**
+This is a trained model of a **QRDQN** agent playing **BreakoutNoFrameskip-v4**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo qrdqn --env BreakoutNoFrameskip-v4 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo qrdqn --env BreakoutNoFrameskip-v4  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo qrdqn --env BreakoutNoFrameskip-v4 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo qrdqn --env BreakoutNoFrameskip-v4  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo qrdqn --env BreakoutNoFrameskip-v4 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo qrdqn --env BreakoutNoFrameskip-v4 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('env_wrapper',
+              ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
+             ('exploration_fraction', 0.025),
+             ('frame_stack', 4),
+             ('gradient_steps', -1),
+             ('n_envs', 8),
+             ('n_timesteps', 10000000.0),
+             ('optimize_memory_usage', False),
+             ('policy', 'CnnPolicy'),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,84 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - qrdqn
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - BreakoutNoFrameskip-v4
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - gradient_steps: -1
+      n_envs: 8
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 1
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 855470999
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - subproc
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,17 @@
+!!python/object/apply:collections.OrderedDict
+- - - env_wrapper
+    - - stable_baselines3.common.atari_wrappers.AtariWrapper
+  - - exploration_fraction
+    - 0.025
+  - - frame_stack
+    - 4
+  - - gradient_steps
+    - -1
+  - - n_envs
+    - 8
+  - - n_timesteps
+    - 10000000.0
+  - - optimize_memory_usage
+    - false
+  - - policy
+    - CnnPolicy

env_kwargs.yml

@@ -0,0 +1 @@
+{}

qrdqn-BreakoutNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2dcc168bfb81fec31087f89d71202675d172371228f319228212053189044e
+size 34005370

qrdqn-BreakoutNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

qrdqn-BreakoutNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:708caafba25288118c699e3ef63b9b8571a8fa565c47d3ece7e55e3ba55fad3c
+size 16764363

qrdqn-BreakoutNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a93b24931b40f22056178a3f3799f9b6cdea69dab4c62d6923092dd03e8176
+size 16763945

qrdqn-BreakoutNoFrameskip-v4/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

qrdqn-BreakoutNoFrameskip-v4/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be95036ae2f707109658355fc798c27a4e2d39a3b9c2f968df3171a32e014ac8
+size 53747

results.json

@@ -0,0 +1 @@
+{"mean_reward": 2.3, "std_reward": 3.0675723300355937, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T13:51:34.932893"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ff4d57e42a2d6584c3d29d79ca62cbed1a081d77f5db0229699ff440aec4a4
+size 10091