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 +15 -15
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- results.json +1 -1
README.md
CHANGED
@@ -10,7 +10,7 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value: -
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: -125.17 +/- 14.09
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
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 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 0x7fb199a5e700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb199a5e790>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb199a5e820>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb199a5e8b0>", "_build": "<function ActorCriticPolicy._build at 0x7fb199a5e940>", "forward": "<function ActorCriticPolicy.forward at 0x7fb199a5e9d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb199a5ea60>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb199a5eaf0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb199a5eb80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb199a5ec10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb199a5eca0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fb199a5f740>"}, "verbose": 0, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 5120, "_total_timesteps": 5000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652289003.7817495, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGba0LwAIKM/kjJmvkM5Fb+Xz1s9Ky90PQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 20, "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": 1024, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-40-generic-x86_64-with-glibc2.31 #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}
|
|
|
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 0x7ff9ed024820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff9ed0248b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff9ed024940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff9ed0249d0>", "_build": "<function ActorCriticPolicy._build at 0x7ff9ed024a60>", "forward": "<function ActorCriticPolicy.forward at 0x7ff9ed024af0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff9ed024b80>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff9ed024c10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff9ed024ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff9ed024d30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff9ed024dc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff9ed0256c0>"}, "verbose": 0, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 5120, "_total_timesteps": 5000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652289955.5168335, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJIDxL6x9NA+BdBKv5Pdk7+HB9E+/P8JPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 20, "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": 1024, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWV+wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjGUvaG9tZS9hbGV4L2FuYWNvbmRhMy9lbnZzL2RlZXAtcmwtY2xhc3MvbGliL3B5dGhvbjMuOS9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMZS9ob21lL2FsZXgvYW5hY29uZGEzL2VudnMvZGVlcC1ybC1jbGFzcy9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-40-generic-x86_64-with-glibc2.31 #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}
|
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 sha256:6b91307ebf8139daccd4ef551d28582a619b42b1d7fc0f2dc61249129bed7bf6
|
3 |
+
size 140922
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,19 +4,19 @@
|
|
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
|
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 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
14 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
15 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
16 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
17 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
-
"_abc_impl": "<_abc._abc_data object at
|
20 |
},
|
21 |
"verbose": 0,
|
22 |
"policy_kwargs": {},
|
@@ -47,7 +47,7 @@
|
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
-
"start_time":
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
@@ -56,7 +56,7 @@
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -69,7 +69,7 @@
|
|
69 |
"_current_progress_remaining": -0.02400000000000002,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
|
|
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 0x7ff9ed024820>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff9ed0248b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff9ed024940>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff9ed0249d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7ff9ed024a60>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7ff9ed024af0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff9ed024b80>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7ff9ed024c10>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff9ed024ca0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff9ed024d30>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff9ed024dc0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc._abc_data object at 0x7ff9ed0256c0>"
|
20 |
},
|
21 |
"verbose": 0,
|
22 |
"policy_kwargs": {},
|
|
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1652289955.5168335,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAJIDxL6x9NA+BdBKv5Pdk7+HB9E+/P8JPgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
69 |
"_current_progress_remaining": -0.02400000000000002,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
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 84829
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97524fcfe29d19c6d7435f53512b0cba9661baaa7148e9dba76d88cfcd5f13cb
|
3 |
size 84829
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43201
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41d1a8d0bb9f773bf59c9132cd25c993b42287814677b0167bb217ca61c1074c
|
3 |
size 43201
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -
|
|
|
1 |
+
{"mean_reward": -125.173321740143, "std_reward": 14.094646454147178, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T20:26:50.806885"}
|