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 +31 -31
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- 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: 270.22 +/- 17.02
|
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 0x7948d58ba8c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7948d58ba950>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7948d58ba9e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7948d58baa70>", "_build": "<function ActorCriticPolicy._build at 0x7948d58bab00>", "forward": "<function ActorCriticPolicy.forward at 0x7948d58bab90>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7948d58bac20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7948d58bacb0>", "_predict": "<function ActorCriticPolicy._predict at 0x7948d58bad40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7948d58badd0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7948d58bae60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7948d58baef0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7948d61d6100>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713207366654886124, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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 0x790da965f9a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x790da965fa30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x790da965fac0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x790da965fb50>", "_build": "<function ActorCriticPolicy._build at 0x790da965fbe0>", "forward": "<function ActorCriticPolicy.forward at 0x790da965fc70>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x790da965fd00>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x790da965fd90>", "_predict": "<function ActorCriticPolicy._predict at 0x790da965fe20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x790da965feb0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x790da965ff40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x790da9664040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x790da9653680>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713207366654886124, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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, "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, "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": 16, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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:ea33d18989853de811624a44d4394304f6268bdc51b3fe7e53c99842df1b8192
|
3 |
+
size 147841
|
ppo-LunarLander-v2/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
|
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": {},
|
@@ -27,7 +27,7 @@
|
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
"start_time": 1713207366654886124,
|
30 |
-
"learning_rate": 0.
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -52,6 +52,21 @@
|
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
"_n_updates": 248,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
@@ -69,7 +84,7 @@
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
-
":serialized:": "
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
@@ -77,23 +92,8 @@
|
|
77 |
"_np_random": null
|
78 |
},
|
79 |
"n_envs": 16,
|
80 |
-
"n_steps": 1024,
|
81 |
-
"gamma": 0.999,
|
82 |
-
"gae_lambda": 0.98,
|
83 |
-
"ent_coef": 0.01,
|
84 |
-
"vf_coef": 0.5,
|
85 |
-
"max_grad_norm": 0.5,
|
86 |
-
"batch_size": 64,
|
87 |
-
"n_epochs": 4,
|
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 |
}
|
|
|
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 0x790da965f9a0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x790da965fa30>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x790da965fac0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x790da965fb50>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x790da965fbe0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x790da965fc70>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x790da965fd00>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x790da965fd90>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x790da965fe20>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x790da965feb0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x790da965ff40>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x790da9664040>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x790da9653680>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
"start_time": 1713207366654886124,
|
30 |
+
"learning_rate": 0.0,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
"_n_updates": 248,
|
55 |
+
"n_steps": 1024,
|
56 |
+
"gamma": 0.999,
|
57 |
+
"gae_lambda": 0.98,
|
58 |
+
"ent_coef": 0.01,
|
59 |
+
"vf_coef": 0.5,
|
60 |
+
"max_grad_norm": 0.5,
|
61 |
+
"batch_size": 64,
|
62 |
+
"n_epochs": 4,
|
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:": "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",
|
|
|
84 |
},
|
85 |
"action_space": {
|
86 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
87 |
+
":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
88 |
"n": "4",
|
89 |
"start": "0",
|
90 |
"_shape": [],
|
|
|
92 |
"_np_random": null
|
93 |
},
|
94 |
"n_envs": 16,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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:d50e5d9678fa9c665ebf4190aa4ef595d1242b3bee117aae577fae5335c96ead
|
3 |
+
size 88490
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 270.21765960613646, "std_reward": 17.018960910934553, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-15T19:55:10.001570"}
|