Retrain PPO model for BipedalWalker-v3 v1
Browse files- .gitattributes +1 -0
- PPO-BipedalWalker-v3.zip +3 -0
- PPO-BipedalWalker-v3/_stable_baselines3_version +1 -0
- PPO-BipedalWalker-v3/data +99 -0
- PPO-BipedalWalker-v3/policy.optimizer.pth +3 -0
- PPO-BipedalWalker-v3/policy.pth +3 -0
- PPO-BipedalWalker-v3/pytorch_variables.pth +3 -0
- PPO-BipedalWalker-v3/system_info.txt +7 -0
- README.md +28 -0
- config.json +1 -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
|
PPO-BipedalWalker-v3.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fcbc9464bf5f2c2f7580837d2a5294427330658666d2780a6c2b78685d65df1
|
3 |
+
size 170637
|
PPO-BipedalWalker-v3/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
PPO-BipedalWalker-v3/data
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7fbc1a8f2680>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbc1a8f2710>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbc1a8f27a0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbc1a8f2830>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fbc1a8f28c0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fbc1a8f2950>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbc1a8f29e0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fbc1a8f2a70>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbc1a8f2b00>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbc1a8f2b90>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbc1a8f2c20>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fbc1a945390>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
24
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
38 |
+
":serialized:": "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",
|
39 |
+
"dtype": "float32",
|
40 |
+
"_shape": [
|
41 |
+
4
|
42 |
+
],
|
43 |
+
"low": "[-1. -1. -1. -1.]",
|
44 |
+
"high": "[1. 1. 1. 1.]",
|
45 |
+
"bounded_below": "[ True True True True]",
|
46 |
+
"bounded_above": "[ True True True True]",
|
47 |
+
"_np_random": null
|
48 |
+
},
|
49 |
+
"n_envs": 6,
|
50 |
+
"num_timesteps": 503808,
|
51 |
+
"_total_timesteps": 500000,
|
52 |
+
"_num_timesteps_at_start": 0,
|
53 |
+
"seed": null,
|
54 |
+
"action_noise": null,
|
55 |
+
"start_time": 1652451543.2770567,
|
56 |
+
"learning_rate": 0.0003,
|
57 |
+
"tensorboard_log": null,
|
58 |
+
"lr_schedule": {
|
59 |
+
":type:": "<class 'function'>",
|
60 |
+
":serialized:": "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"
|
61 |
+
},
|
62 |
+
"_last_obs": {
|
63 |
+
":type:": "<class 'numpy.ndarray'>",
|
64 |
+
":serialized:": "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"
|
65 |
+
},
|
66 |
+
"_last_episode_starts": {
|
67 |
+
":type:": "<class 'numpy.ndarray'>",
|
68 |
+
":serialized:": "gAWVeQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYGAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLBoWUjAFDlHSUUpQu"
|
69 |
+
},
|
70 |
+
"_last_original_obs": null,
|
71 |
+
"_episode_num": 0,
|
72 |
+
"use_sde": false,
|
73 |
+
"sde_sample_freq": -1,
|
74 |
+
"_current_progress_remaining": -0.007616000000000067,
|
75 |
+
"ep_info_buffer": {
|
76 |
+
":type:": "<class 'collections.deque'>",
|
77 |
+
":serialized:": "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"
|
78 |
+
},
|
79 |
+
"ep_success_buffer": {
|
80 |
+
":type:": "<class 'collections.deque'>",
|
81 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
82 |
+
},
|
83 |
+
"_n_updates": 1148,
|
84 |
+
"n_steps": 2048,
|
85 |
+
"gamma": 0.999,
|
86 |
+
"gae_lambda": 0.95,
|
87 |
+
"ent_coef": 0.0,
|
88 |
+
"vf_coef": 0.5,
|
89 |
+
"max_grad_norm": 0.5,
|
90 |
+
"batch_size": 64,
|
91 |
+
"n_epochs": 7,
|
92 |
+
"clip_range": {
|
93 |
+
":type:": "<class 'function'>",
|
94 |
+
":serialized:": "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"
|
95 |
+
},
|
96 |
+
"clip_range_vf": null,
|
97 |
+
"normalize_advantage": true,
|
98 |
+
"target_kl": null
|
99 |
+
}
|
PPO-BipedalWalker-v3/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35515a12c916cb6f51d5916cb89892e8100c754c51def7435d3d5a356a8f245c
|
3 |
+
size 101783
|
PPO-BipedalWalker-v3/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f99ee6dbe7525bc345f7077e4e254d6177daa30201b7a2b651f17c4418e74551
|
3 |
+
size 51710
|
PPO-BipedalWalker-v3/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-BipedalWalker-v3/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.10.107+-x86_64-with-debian-bullseye-sid #1 SMP Sun Apr 24 15:04:08 UTC 2022
|
2 |
+
Python: 3.7.12
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.9.1
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
README.md
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- BipedalWalker-v3
|
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: 226.04 +/- 113.91
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: BipedalWalker-v3
|
20 |
+
type: BipedalWalker-v3
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **BipedalWalker-v3**
|
24 |
+
This is a trained model of a **PPO** agent playing **BipedalWalker-v3** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
25 |
+
|
26 |
+
## Usage (with Stable-baselines3)
|
27 |
+
TODO: Add your code
|
28 |
+
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7fbc1a8f2680>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbc1a8f2710>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbc1a8f27a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbc1a8f2830>", "_build": "<function ActorCriticPolicy._build at 0x7fbc1a8f28c0>", "forward": "<function ActorCriticPolicy.forward at 0x7fbc1a8f2950>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbc1a8f29e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fbc1a8f2a70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbc1a8f2b00>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbc1a8f2b90>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbc1a8f2c20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fbc1a945390>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [24], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "bounded_below": "[ True True True True]", "bounded_above": "[ True True True True]", "_np_random": null}, "n_envs": 6, "num_timesteps": 503808, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652451543.2770567, "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:": "gAWVeQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYGAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLBoWUjAFDlHSUUpQu"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1148, "n_steps": 2048, "gamma": 0.999, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 7, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.107+-x86_64-with-debian-bullseye-sid #1 SMP Sun Apr 24 15:04:08 UTC 2022", "Python": "3.7.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.9.1", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8414ff0a82d1ed8f5649f708445f6a6e8792dfd519775724977adbde515b03f
|
3 |
+
size 447954
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 226.0374212252876, "std_reward": 113.90725565066312, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-13T14:32:21.917282"}
|