Hello RL with HF
Browse files- .gitattributes +1 -0
- README.md +36 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +94 -0
- ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2/policy.pth +3 -0
- ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2/system_info.txt +7 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- LunarLander-v2
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 10.91 +/- 113.77
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
+
|
27 |
+
## Usage (with Stable-baselines3)
|
28 |
+
TODO: Add your code
|
29 |
+
|
30 |
+
|
31 |
+
```python
|
32 |
+
from stable_baselines3 import ...
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
...
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f2136a8eef0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2136a8ef80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2136a94050>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2136a940e0>", "_build": "<function ActorCriticPolicy._build at 0x7f2136a94170>", "forward": "<function ActorCriticPolicy.forward at 0x7f2136a94200>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2136a94290>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2136a94320>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2136a943b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2136a94440>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2136a944d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f2136ad5c30>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1655152055.231936, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVdhAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMI5PT1fM2EY0CUhpRSlIwBbJRN6AOMAXSUR0B/kpBHCoCNdX2UKGgGaAloD0MITwMGSZ9mS0CUhpRSlGgVTegDaBZHQH+sQ5FPSD11fZQoaAZoCWgPQwgWhsjp6+NTQJSGlFKUaBVN6ANoFkdAf7EGxlg+hXV9lChoBmgJaA9DCHe/CvBdy2FAlIaUUpRoFU3oA2gWR0B/tusLfDUFdX2UKGgGaAloD0MIP+JXrOEMR0CUhpRSlGgVTegDaBZHQH/Ljd56dDp1fZQoaAZoCWgPQwiwcJLmj7VbQJSGlFKUaBVN6ANoFkdAf9/LF4s3AHV9lChoBmgJaA9DCOmY84x9BmBAlIaUUpRoFU3oA2gWR0B/3+iudPLxdX2UKGgGaAloD0MIs5lDUgsl87+UhpRSlGgVTegDaBZHQH/i/m9xp+N1fZQoaAZoCWgPQwiYpZ2ay7ZVQJSGlFKUaBVN6ANoFkdAf+Z4//vOQnV9lChoBmgJaA9DCMpuZvSj4dq/lIaUUpRoFU0eAWgWR0B/6Z3qzJIUdX2UKGgGaAloD0MIp+uJrgtsVUCUhpRSlGgVTegDaBZHQH/roClrM1V1fZQoaAZoCWgPQwiY2lIHeQ0VwJSGlFKUaBVL7WgWR0B/8webNKRMdX2UKGgGaAloD0MI2jujrUrCFMCUhpRSlGgVTegDaBZHQH/3M+qzZ6F1fZQoaAZoCWgPQwhOYDqt27BYQJSGlFKUaBVN6ANoFkdAgAIyPEKmbnV9lChoBmgJaA9DCAx2w7ZFv1HAlIaUUpRoFUvsaBZHQIAOv1nM+vB1fZQoaAZoCWgPQwg3cAfqlEtTQJSGlFKUaBVN6ANoFkdAgCIla8pTdnV9lChoBmgJaA9DCM0FLo81nVxAlIaUUpRoFU3oA2gWR0CAK1pJwsGxdX2UKGgGaAloD0MI2XdF8L8tVkCUhpRSlGgVTegDaBZHQIA3yXnhbW51fZQoaAZoCWgPQwjeq1Ym/H9QQJSGlFKUaBVN6ANoFkdAgEcVEd/8VHV9lChoBmgJaA9DCAUVVb/Se0DAlIaUUpRoFU0MAWgWR0CAfAS6DoQndX2UKGgGaAloD0MIQ+VfyytwYECUhpRSlGgVTegDaBZHQICJjh73PAx1fZQoaAZoCWgPQwhCCMiXUEBVQJSGlFKUaBVN6ANoFkdAgI7p9iMHbHV9lChoBmgJaA9DCKSLTSuF+DNAlIaUUpRoFU3oA2gWR0CAmR7tzCDVdX2UKGgGaAloD0MI9KRMami9WkCUhpRSlGgVTegDaBZHQICjW+bmU4d1fZQoaAZoCWgPQwimXyLeOnNXQJSGlFKUaBVN6ANoFkdAgKNs7U5MlHV9lChoBmgJaA9DCGoSvCGNqEdAlIaUUpRoFU3oA2gWR0CApPmDlHSXdX2UKGgGaAloD0MIPs40YfvNOsCUhpRSlGgVS7hoFkdAgKWpeVs1sXV9lChoBmgJaA9DCN0LzApFjExAlIaUUpRoFU3oA2gWR0CAptBUJfICdX2UKGgGaAloD0MIy2d5HtzCWECUhpRSlGgVTegDaBZHQICooY77sOZ1fZQoaAZoCWgPQwhvSKMCJ2MiwJSGlFKUaBVLwmgWR0CAqyTPjXFtdX2UKGgGaAloD0MIRE/KpIaSU0CUhpRSlGgVTegDaBZHQICt/pGFzuF1fZQoaAZoCWgPQwh6ceKrHRpeQJSGlFKUaBVN6ANoFkdAgLAloL5RCXV9lChoBmgJaA9DCJc8npYf3D5AlIaUUpRoFU3oA2gWR0CAtqlw97ngdX2UKGgGaAloD0MI0lJ5O8LKXECUhpRSlGgVTegDaBZHQIDDEQVbiZR1fZQoaAZoCWgPQwiifEELCcAsQJSGlFKUaBVNIAFoFkdAgMptlRP423V9lChoBmgJaA9DCNv66T9rejzAlIaUUpRoFU0QAWgWR0CAy2DhcZ+AdX2UKGgGaAloD0MIuXL2zmjqXECUhpRSlGgVTegDaBZHQIDSZEYwZfl1fZQoaAZoCWgPQwjkSdI1kwdUQJSGlFKUaBVN6ANoFkdAgONdkBjnWHV9lChoBmgJaA9DCHb+7bJfIlxAlIaUUpRoFU3oA2gWR0CA7QaPS2H+dX2UKGgGaAloD0MI3WETmbmQOECUhpRSlGgVS/9oFkdAgPGF4C6pYXV9lChoBmgJaA9DCDW4rS0891xAlIaUUpRoFU3oA2gWR0CBHyxptaZAdX2UKGgGaAloD0MID52ed+O+ZECUhpRSlGgVTe0CaBZHQIEhmcjJMg51fZQoaAZoCWgPQwhHsHH9O1FgQJSGlFKUaBVN6ANoFkdAgTZxplBhQXV9lChoBmgJaA9DCLH8+bbgVGZAlIaUUpRoFU3BA2gWR0CBPUMyad+YdX2UKGgGaAloD0MIc2cmGM7cWkCUhpRSlGgVTegDaBZHQIE/Nu3trsV1fZQoaAZoCWgPQwjcoPZbO05lQJSGlFKUaBVN6ANoFkdAgT9DIq9XcXV9lChoBmgJaA9DCOj6PhwkGVdAlIaUUpRoFU3oA2gWR0CBQJ6ab4JvdX2UKGgGaAloD0MI5iSUvhBrWkCUhpRSlGgVTegDaBZHQIFD3cDbJwN1fZQoaAZoCWgPQwht5pDUQoU6wJSGlFKUaBVNOwFoFkdAgUiusT37DXV9lChoBmgJaA9DCEFl/PuM2VlAlIaUUpRoFU3oA2gWR0CBS4RAbADadX2UKGgGaAloD0MIL6NYbmmKWUCUhpRSlGgVTegDaBZHQIFTDCJoCdV1fZQoaAZoCWgPQwjDZoALsvlYQJSGlFKUaBVN6ANoFkdAgWEtEgGKRHV9lChoBmgJaA9DCAG+27xxXjPAlIaUUpRoFU0zAWgWR0CBZDHR1HOKdX2UKGgGaAloD0MIoIfaNozQSkCUhpRSlGgVTegDaBZHQIFpp+pfhMt1fZQoaAZoCWgPQwgiNe1imstdQJSGlFKUaBVN6ANoFkdAgWq0CA+Y+nV9lChoBmgJaA9DCHUDBd7JFy7AlIaUUpRoFUvaaBZHQIF9s8zQ/ot1fZQoaAZoCWgPQwijO4idKbdYQJSGlFKUaBVN6ANoFkdAgYWKaw2VFHV9lChoBmgJaA9DCFfPSe8bSllAlIaUUpRoFU3oA2gWR0CBkOV0Lc9GdX2UKGgGaAloD0MIIv/MID51X0CUhpRSlGgVTegDaBZHQIGWQtvn8sN1fZQoaAZoCWgPQwj3H5kOnepcQJSGlFKUaBVN6ANoFkdAgaCgI6bONnV9lChoBmgJaA9DCCZtqu6RcGHAlIaUUpRoFU2lA2gWR0CB30ZhKDkEdX2UKGgGaAloD0MIi6VIvhIRX0CUhpRSlGgVTegDaBZHQIHfaCSRr8B1fZQoaAZoCWgPQwgG9MKdC5pTQJSGlFKUaBVN6ANoFkdAgeazA31jAnV9lChoBmgJaA9DCPDDQUKUf1lAlIaUUpRoFU3oA2gWR0CB6hWKdhAodX2UKGgGaAloD0MIkSbeAZ4YRkCUhpRSlGgVTegDaBZHQIHtkjZ+QU51fZQoaAZoCWgPQwgn3gGetBhbQJSGlFKUaBVN6ANoFkdAgfKtwR5C4XV9lChoBmgJaA9DCBrCMcseX2JAlIaUUpRoFU3oA2gWR0CB9XprULDydX2UKGgGaAloD0MIFvw2xHhNXkCUhpRSlGgVTegDaBZHQIH8+NvOyFB1fZQoaAZoCWgPQwhorz4e+jxZQJSGlFKUaBVN6ANoFkdAgg60iY9gW3V9lChoBmgJaA9DCKmI00m2qhlAlIaUUpRoFU3oA2gWR0CCFHyksSTRdX2UKGgGaAloD0MIKXef46NTWUCUhpRSlGgVTegDaBZHQIIVmZgG8mN1fZQoaAZoCWgPQwithsQ9lkFQwJSGlFKUaBVNMwFoFkdAgh0mM4tHx3V9lChoBmgJaA9DCCQLmMCtex3AlIaUUpRoFUv0aBZHQIIdbkhib2F1fZQoaAZoCWgPQwhqTl5kAghXQJSGlFKUaBVN6ANoFkdAginTJ6po9XV9lChoBmgJaA9DCFwbKsb5r2PAlIaUUpRoFU2RA2gWR0CCL+/jbSJCdX2UKGgGaAloD0MIt376z5rDXkCUhpRSlGgVTegDaBZHQIIxUqpcX3x1fZQoaAZoCWgPQwg+0AoMWdJhQJSGlFKUaBVN6ANoFkdAgkCJzcRDkXV9lChoBmgJaA9DCPFJJxJMvlpAlIaUUpRoFU3oA2gWR0CCSxw4KhL5dX2UKGgGaAloD0MI7KF9rOB9RsCUhpRSlGgVS+VoFkdAglC109yLh3V9lChoBmgJaA9DCOqu7ILBtes/lIaUUpRoFU0BAWgWR0CCd5mEoOQRdX2UKGgGaAloD0MITKYKRiVKWkCUhpRSlGgVTegDaBZHQIKKxq7Ackt1fZQoaAZoCWgPQwjPhZFe1ExQQJSGlFKUaBVN6ANoFkdAgorr2QGOdXV9lChoBmgJaA9DCBi0kIDRcV5AlIaUUpRoFU3oA2gWR0CCke0XP7emdX2UKGgGaAloD0MIb6DAO/lPVECUhpRSlGgVTegDaBZHQIKVFS/CZWt1fZQoaAZoCWgPQwgfFJSilehRwJSGlFKUaBVNVgFoFkdAgpUb0OEuhHV9lChoBmgJaA9DCMk9Xd2x6kHAlIaUUpRoFU0eAWgWR0CCl3A+pwS8dX2UKGgGaAloD0MId0mcFVE0W0CUhpRSlGgVTegDaBZHQIKYXtUn5SF1fZQoaAZoCWgPQwguO8Q/bGJWQJSGlFKUaBVN6ANoFkdAgpyaj3225XV9lChoBmgJaA9DCBIvT+eK8gDAlIaUUpRoFUvoaBZHQIKkspkPMB91fZQoaAZoCWgPQwjl1TkGZKMwQJSGlFKUaBVLt2gWR0CCqraTwDvFdX2UKGgGaAloD0MIuVUQA113X0CUhpRSlGgVTegDaBZHQIK0wMF2V3V1fZQoaAZoCWgPQwjcgxCQL91KwJSGlFKUaBVL8GgWR0CCtlpSrHU+dX2UKGgGaAloD0MIjSrDuBvyWECUhpRSlGgVTegDaBZHQIK5uYplSTB1fZQoaAZoCWgPQwjq6SPwh/9VQJSGlFKUaBVN6ANoFkdAgrqq4hEBsHV9lChoBmgJaA9DCJEnSddMqktAlIaUUpRoFU3oA2gWR0CCwJrsSkCWdX2UKGgGaAloD0MILuQR3EhgUUCUhpRSlGgVTegDaBZHQILA1D6WPcV1fZQoaAZoCWgPQwhoImx4elBYQJSGlFKUaBVN6ANoFkdAgsp6NuLrHHV9lChoBmgJaA9DCFA1ejVA7GhAlIaUUpRoFU1WAmgWR0CC1u3OObRXdX2UKGgGaAloD0MIZ341BwjAUECUhpRSlGgVTegDaBZHQILvAaaTfSB1fZQoaAZoCWgPQwiEud3LfcVSQJSGlFKUaBVN6ANoFkdAgvGpBHCoCXVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95b18dafa4ad279e4b6f7c1b1bf299b371a3e164988d3b629693db6a647ed756
|
3 |
+
size 144143
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
+
"__module__": "stable_baselines3.common.policies",
|
6 |
+
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7f2136a8eef0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2136a8ef80>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2136a94050>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2136a940e0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f2136a94170>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f2136a94200>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2136a94290>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f2136a94320>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2136a943b0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2136a94440>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2136a944d0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f2136ad5c30>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "gASVwwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBVudW1weS5jb3JlLm11bHRpYXJyYXmUjAxfcmVjb25zdHJ1Y3SUk5RoBowHbmRhcnJheZSTlEsAhZRDAWKUh5RSlChLAUsIhZRoColDIAAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lHSUYowEaGlnaJRoEmgUSwCFlGgWh5RSlChLAUsIhZRoColDIAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/lHSUYowNYm91bmRlZF9iZWxvd5RoEmgUSwCFlGgWh5RSlChLAUsIhZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDCAAAAAAAAAAAlHSUYowNYm91bmRlZF9hYm92ZZRoEmgUSwCFlGgWh5RSlChLAUsIhZRoKolDCAAAAAAAAAAAlHSUYowKX25wX3JhbmRvbZROdWIu",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 507904,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1655152055.231936,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
+
},
|
57 |
+
"_last_obs": {
|
58 |
+
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 124,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d63e38e2e28461db3f16825b0bfe8fc8cd3902793b19683a657f9e606f0def75
|
3 |
+
size 84829
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7d989dfaac6f25a396bfc3a651b8b8767bf5c0f781f984952997420637cf024
|
3 |
+
size 43201
|
ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44f452c7c9870893bc2b5c72e1dd604808de2d21f73d7803bfc0ee6929b9436d
|
3 |
+
size 252148
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 10.909158934794737, "std_reward": 113.7681522277682, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-13T20:44:09.025944"}
|