dlantonia commited on
Commit
7c0ac3b
·
verified ·
1 Parent(s): e5ce6dd

Initial commit

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: BipedalWalker-v3
17
  metrics:
18
  - type: mean_reward
19
- value: 293.12 +/- 1.82
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: BipedalWalker-v3
17
  metrics:
18
  - type: mean_reward
19
+ value: 271.07 +/- 48.16
20
  name: mean_reward
21
  verified: false
22
  ---
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3492371912
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 735497209
60
  - - storage
61
  - null
62
  - - study_name
ppo-BipedalWalker-v3.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f526853c8ce8a889a70d32107bcf4c254c85d8e24cf2fc8c2369cf8e7e839e85
3
  size 184202
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48dd62b89508c002d36f4b8e8e89961f546ac34c3c0416aa02cd50978fc969c9
3
  size 184202
ppo-BipedalWalker-v3/data CHANGED
@@ -4,20 +4,20 @@
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7b457e6991b0>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b457e699240>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b457e6992d0>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b457e699360>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7b457e6993f0>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7b457e699480>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b457e699510>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b457e6995a0>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x7b457e699630>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b457e6996c0>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b457e699750>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b457e6997e0>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x7b457e69ccc0>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
@@ -26,7 +26,7 @@
26
  "_num_timesteps_at_start": 0,
27
  "seed": 0,
28
  "action_noise": null,
29
- "start_time": 1722955520067779177,
30
  "learning_rate": {
31
  ":type:": "<class 'function'>",
32
  ":serialized:": "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"
@@ -39,7 +39,7 @@
39
  },
40
  "_last_original_obs": {
41
  ":type:": "<class 'numpy.ndarray'>",
42
- ":serialized:": "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"
43
  },
44
  "_episode_num": 0,
45
  "use_sde": false,
@@ -48,7 +48,7 @@
48
  "_stats_window_size": 100,
49
  "ep_info_buffer": {
50
  ":type:": "<class 'collections.deque'>",
51
- ":serialized:": "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"
52
  },
53
  "ep_success_buffer": {
54
  ":type:": "<class 'collections.deque'>",
@@ -98,14 +98,14 @@
98
  "__module__": "stable_baselines3.common.buffers",
99
  "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
100
  "__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ",
101
- "__init__": "<function RolloutBuffer.__init__ at 0x7b457e7fbf40>",
102
- "reset": "<function RolloutBuffer.reset at 0x7b457e7fc040>",
103
- "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7b457e7fc0d0>",
104
- "add": "<function RolloutBuffer.add at 0x7b457e7fc160>",
105
- "get": "<function RolloutBuffer.get at 0x7b457e7fc1f0>",
106
- "_get_samples": "<function RolloutBuffer._get_samples at 0x7b457e7fc280>",
107
  "__abstractmethods__": "frozenset()",
108
- "_abc_impl": "<_abc._abc_data object at 0x7b457e9e3940>"
109
  },
110
  "rollout_buffer_kwargs": {},
111
  "batch_size": 64,
 
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7d2b5c96d1b0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d2b5c96d240>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d2b5c96d2d0>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d2b5c96d360>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7d2b5c96d3f0>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7d2b5c96d480>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d2b5c96d510>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d2b5c96d5a0>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7d2b5c96d630>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d2b5c96d6c0>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d2b5c96d750>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d2b5c96d7e0>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7d2b5c978100>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
 
26
  "_num_timesteps_at_start": 0,
27
  "seed": 0,
28
  "action_noise": null,
29
+ "start_time": 1723039659154216693,
30
  "learning_rate": {
31
  ":type:": "<class 'function'>",
32
  ":serialized:": "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"
 
39
  },
40
  "_last_original_obs": {
41
  ":type:": "<class 'numpy.ndarray'>",
42
+ ":serialized:": "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"
43
  },
44
  "_episode_num": 0,
45
  "use_sde": false,
 
48
  "_stats_window_size": 100,
49
  "ep_info_buffer": {
50
  ":type:": "<class 'collections.deque'>",
51
+ ":serialized:": "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"
52
  },
53
  "ep_success_buffer": {
54
  ":type:": "<class 'collections.deque'>",
 
98
  "__module__": "stable_baselines3.common.buffers",
99
  "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
100
  "__doc__": "\n Rollout buffer used in on-policy algorithms like A2C/PPO.\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to classic advantage when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ",
101
+ "__init__": "<function RolloutBuffer.__init__ at 0x7d2b5cad3f40>",
102
+ "reset": "<function RolloutBuffer.reset at 0x7d2b5cad4040>",
103
+ "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7d2b5cad40d0>",
104
+ "add": "<function RolloutBuffer.add at 0x7d2b5cad4160>",
105
+ "get": "<function RolloutBuffer.get at 0x7d2b5cad41f0>",
106
+ "_get_samples": "<function RolloutBuffer._get_samples at 0x7d2b5cad4280>",
107
  "__abstractmethods__": "frozenset()",
108
+ "_abc_impl": "<_abc._abc_data object at 0x7d2b5ca5c6c0>"
109
  },
110
  "rollout_buffer_kwargs": {},
111
  "batch_size": 64,
ppo-BipedalWalker-v3/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ba93d7d50cd32cd5d549f610919fc377a0486b26ca565d20f5d43f461bd4eb4
3
  size 105633
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30cf7914990f569fd3f3fc1957d90d1ff700f49e64a91cd0fe0a69b57afae83a
3
  size 105633
ppo-BipedalWalker-v3/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b091967e4711a23e3f7bd5fd7299e790465c862beed19ff07895108b74c12f0
3
  size 52271
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daed280c430e21c7ea0bab5c85c3488baebee63c77578ff6765fb087fd0e0189
3
  size 52271
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 293.11860790000003, "std_reward": 1.8170609875807906, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-06T16:44:04.309936"}
 
1
+ {"mean_reward": 271.0698341, "std_reward": 48.162342745229495, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-07T15:56:35.996406"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3c8ecc89239b51f2ea3015f99189e65ea6eb9d2db6456ff4659f6bc0b5b49a2
3
- size 129193
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892610bceb36ab5ae495725d9e74c46258fadf3a4901d2169096a730f8243721
3
+ size 130614
vec_normalize.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:514f7cf1fe61d8a79923bf97b86cda39c0808273cad476dee4d1b74c63bc4ce3
3
  size 6067
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6cb8f54daf17cba99c86b62c82aea5b5ccbce1405529a58d90090200a15a6c8
3
  size 6067