Upload LunarLander trained
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +39 -39
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- 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: 291.72 +/- 16.72
|
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 0x7f4c13208700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f4c13208790>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f4c13208820>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f4c132088b0>", "_build": "<function ActorCriticPolicy._build at 0x7f4c13208940>", "forward": "<function ActorCriticPolicy.forward at 0x7f4c132089d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f4c13208a60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f4c13208af0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f4c13208b80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f4c13208c10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f4c13208ca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f4c13208d30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f4c131f9a00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1013760, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688675799107941303, "learning_rate": 0.0, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYUAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksUhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.013759999999999994, "_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": 1060, "n_steps": 2304, "gamma": 0.999, "gae_lambda": 0.96, "ent_coef": 0.018, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 256, "n_epochs": 20, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 20, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 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 0x7f53c82da200>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f53c82da290>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f53c82da320>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f53c82da3b0>", "_build": "<function ActorCriticPolicy._build at 0x7f53c82da440>", "forward": "<function ActorCriticPolicy.forward at 0x7f53c82da4d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f53c82da560>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f53c82da5f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f53c82da680>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f53c82da710>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f53c82da7a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f53c82da830>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f53c82dc9c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 829440, "_total_timesteps": 800000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688781573557204044, "learning_rate": 0.00029, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYUAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksUhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.036799999999999944, "_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": 2190, "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": 20, "n_steps": 2304, "gamma": 0.999, "gae_lambda": 0.96, "ent_coef": 0.018, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 512, "n_epochs": 30, "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 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 sha256:1caebb8e74e8fd762408fd4c87c05be08ee5e7d8256e8d2ae17cfb84bb524133
|
3 |
+
size 146798
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,34 +4,34 @@
|
|
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": 1,
|
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.
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -41,35 +41,20 @@
|
|
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 |
-
"n_steps": 2304,
|
56 |
-
"gamma": 0.999,
|
57 |
-
"gae_lambda": 0.96,
|
58 |
-
"ent_coef": 0.018,
|
59 |
-
"vf_coef": 0.5,
|
60 |
-
"max_grad_norm": 0.5,
|
61 |
-
"batch_size": 256,
|
62 |
-
"n_epochs": 20,
|
63 |
-
"clip_range": {
|
64 |
-
":type:": "<class 'function'>",
|
65 |
-
":serialized:": "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"
|
66 |
-
},
|
67 |
-
"clip_range_vf": null,
|
68 |
-
"normalize_advantage": true,
|
69 |
-
"target_kl": null,
|
70 |
"observation_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
72 |
-
":serialized:": "
|
73 |
"dtype": "float32",
|
74 |
"bounded_below": "[ True True True True True True True True]",
|
75 |
"bounded_above": "[ True True True True True True True True]",
|
@@ -84,7 +69,7 @@
|
|
84 |
},
|
85 |
"action_space": {
|
86 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
87 |
-
":serialized:": "
|
88 |
"n": "4",
|
89 |
"start": "0",
|
90 |
"_shape": [],
|
@@ -92,8 +77,23 @@
|
|
92 |
"_np_random": null
|
93 |
},
|
94 |
"n_envs": 20,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
95 |
"lr_schedule": {
|
96 |
":type:": "<class 'function'>",
|
97 |
-
":serialized:": "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
|
98 |
}
|
99 |
}
|
|
|
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 0x7f53c82da200>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f53c82da290>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f53c82da320>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f53c82da3b0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f53c82da440>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f53c82da4d0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f53c82da560>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f53c82da5f0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f53c82da680>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f53c82da710>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f53c82da7a0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f53c82da830>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f53c82dc9c0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 829440,
|
25 |
+
"_total_timesteps": 800000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1688781573557204044,
|
30 |
+
"learning_rate": 0.00029,
|
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'>",
|
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.036799999999999944,
|
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": 2190,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
"dtype": "float32",
|
59 |
"bounded_below": "[ True True True True True True True True]",
|
60 |
"bounded_above": "[ True True True True True True True True]",
|
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
|
|
77 |
"_np_random": null
|
78 |
},
|
79 |
"n_envs": 20,
|
80 |
+
"n_steps": 2304,
|
81 |
+
"gamma": 0.999,
|
82 |
+
"gae_lambda": 0.96,
|
83 |
+
"ent_coef": 0.018,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 512,
|
87 |
+
"n_epochs": 30,
|
88 |
+
"clip_range": {
|
89 |
+
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null,
|
95 |
"lr_schedule": {
|
96 |
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
}
|
99 |
}
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7213612164e35b7f38d267b37904417fa8cd2bf5fd005d4da505cda7d4294c2b
|
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 sha256:30b637385a128143cf8a8c21dc715ff826943961edca4640e1e5a0455cad0694
|
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": 291.7190389, "std_reward": 16.72192643180933, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-08T02:08:16.895007"}
|