ShaileshAppukuttan
commited on
Commit
•
00c186e
1
Parent(s):
93e9b25
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +24 -24
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: LunarLander-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 292.09 +/- 15.90
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +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 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 ", "__init__": "<function ActorCriticPolicy.__init__ at 0x79226cf37be0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79226cf37c70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79226cf37d00>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79226cf37d90>", "_build": "<function ActorCriticPolicy._build at 0x79226cf37e20>", "forward": "<function ActorCriticPolicy.forward at 0x79226cf37eb0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79226cf37f40>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x792208cf0040>", "_predict": "<function ActorCriticPolicy._predict at 0x792208cf00d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x792208cf0160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x792208cf01f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x792208cf0280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x792208cec240>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1690999078986428947, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAALM7m71pEbo+CDYdPiQOc77ss009bpXlvQAAAAAAAAAAU6q1PvDiPz+8YjG9Ngi/vsyfVj64JFq+AAAAAAAAAAAmlOM9hcuyuS7IKTris8c0w9j0ujlNRrkAAAAAAACAP6OXoT6BLXs//nJ+PtwVtb4xIbE+qNxkvQAAAAAAAAAAACwFvXu6oLpI5Ts71Tghtd84lDljUli6AACAPwAAgD+AxRG9BmhXP3HBPz3w4qe+k10PvcNlCj0AAAAAAAAAAI3sQb7yARc/p2yYPr2Mm776JuG8Bp2EPQAAAAAAAAAAk3+QvgUYhD/u0Fu+/hm6vpsesb41rwk+AAAAAAAAAABa9+W97GHTufjmjzwpQHo85gqpO5vuW70AAIA/AAAAADP+qjwpDDu6HXTWur6Hl7Ukbu+62D/+OQAAgD8AAIA/AE+PvYtqIz8PHhs+esaSvj8evTxiUas9AAAAAAAAAAAackw+y0qdP84xsD7lfeu+GWGEPhJmPj0AAAAAAAAAAM2OVL1ck2C6TxdBtPOZC6+2NpG5st+uMwAAgD8AAIA/MyOCO+pLtT8F880++XB4Pn6Slrs/mrq9AAAAAAAAAAAggjW+o8OHP4gR771m83q+DmmIvuIOwrwAAAAAAAAAAM1aHj0pFCS6btEGNF1A9i+K6zS7Hc6pswAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAABAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
|
|
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 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 ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7eec88116320>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eec881163b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eec88116440>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eec881164d0>", "_build": "<function ActorCriticPolicy._build at 0x7eec88116560>", "forward": "<function ActorCriticPolicy.forward at 0x7eec881165f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eec88116680>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eec88116710>", "_predict": "<function ActorCriticPolicy._predict at 0x7eec881167a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eec88116830>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eec881168c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eec88116950>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7eec4140ae80>"}, "verbose": 0, "policy_kwargs": {}, "num_timesteps": 10027008, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1691001288186353771, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0027007999999999477, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 612, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 32, "n_steps": 2048, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1c69482db9f3f4849ee965259088910eeaa5a06d40645f6dfbcbe6f32c0fba4
|
3 |
+
size 147325
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,54 +4,54 @@
|
|
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
|
8 |
-
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at
|
9 |
-
"reset_noise": "<function ActorCriticPolicy.reset_noise at
|
10 |
-
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at
|
11 |
-
"_build": "<function ActorCriticPolicy._build at
|
12 |
-
"forward": "<function ActorCriticPolicy.forward at
|
13 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
-
"verbose":
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
-
":serialized:": "
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
-
"_current_progress_remaining": -0.
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
@@ -76,8 +76,8 @@
|
|
76 |
"dtype": "int64",
|
77 |
"_np_random": null
|
78 |
},
|
79 |
-
"n_envs":
|
80 |
-
"n_steps":
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
83 |
"ent_coef": 0.01,
|
|
|
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 0x7eec88116320>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eec881163b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eec88116440>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eec881164d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7eec88116560>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7eec881165f0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7eec88116680>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eec88116710>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7eec881167a0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eec88116830>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eec881168c0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7eec88116950>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7eec4140ae80>"
|
21 |
},
|
22 |
+
"verbose": 0,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 10027008,
|
25 |
+
"_total_timesteps": 10000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1691001288186353771,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.0027007999999999477,
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 612,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
|
|
76 |
"dtype": "int64",
|
77 |
"_np_random": null
|
78 |
},
|
79 |
+
"n_envs": 32,
|
80 |
+
"n_steps": 2048,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
83 |
"ent_coef": 0.01,
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4201a1df343cbf47e900a5626e6489c5cf5fddf5c595211fb1892b839547f2fc
|
3 |
size 87929
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43329
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd0a21dc36b99e2537d2ff3992a0f7ecccc4c9c2c604ff5cd979b21bc5b0a1cd
|
3 |
size 43329
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 292.08801770534205, "std_reward": 15.902310587657984, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-02T20:37:28.716538"}
|