alexmelekhin
commited on
Commit
•
903b9b3
1
Parent(s):
5808f66
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 +19 -19
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +2 -2
- 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: -119.23 +/- 38.94
|
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 0x7f31285f9ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f31285f9f70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f31285fd040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f31285fd0d0>", "_build": "<function ActorCriticPolicy._build at 0x7f31285fd160>", "forward": "<function ActorCriticPolicy.forward at 0x7f31285fd1f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f31285fd280>", "_predict": "<function ActorCriticPolicy._predict at 0x7f31285fd310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f31285fd3a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f31285fd430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f31285fd4c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f31285f5cf0>"}, "verbose": 1, "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": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652264726.9426453, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 124, "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, "system_info": {"OS": "Linux-5.13.0-40-generic-x86_64-with-glibc2.10 #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022", "Python": "3.8.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.12.0a0+bd13bc6", "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 0x7f2590ef2a60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2590ef2af0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2590ef2b80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2590ef2c10>", "_build": "<function ActorCriticPolicy._build at 0x7f2590ef2ca0>", "forward": "<function ActorCriticPolicy.forward at 0x7f2590ef2d30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2590ef2dc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2590ef2e50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2590ef2ee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2590ef2f70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2590eef040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f2590ee7990>"}, "verbose": 1, "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": 16, "num_timesteps": 114688, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652343939.5835752, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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": -0.1468799999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 28, "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, "system_info": {"OS": "Linux-5.13.0-40-generic-x86_64-with-glibc2.10 #45~20.04.1-Ubuntu SMP Mon Apr 4 09:38:31 UTC 2022", "Python": "3.8.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.12.0a0+bd13bc6", "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:caae552f0a60a9e8632317b3037a158e0d8aefed43d2917c75c5df0aec1db4f1
|
3 |
+
size 147039
|
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_data object at
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
@@ -42,12 +42,12 @@
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
-
"num_timesteps":
|
46 |
-
"_total_timesteps":
|
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'>",
|
@@ -66,16 +66,16 @@
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": -0.
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
|
|
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 0x7f2590ef2a60>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2590ef2af0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2590ef2b80>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2590ef2c10>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f2590ef2ca0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f2590ef2d30>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2590ef2dc0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f2590ef2e50>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2590ef2ee0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2590ef2f70>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2590eef040>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f2590ee7990>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 114688,
|
46 |
+
"_total_timesteps": 100000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1652343939.5835752,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
|
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.1468799999999999,
|
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'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 28,
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
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 87865
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6625ae2efc2729a2d2ae192e8fba94a241ab0be1bb82fd87dd2387ee2ee0585e
|
3 |
size 87865
|
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:d99e05af25d8c63fef65ac7c045ac6f1d0dd652c1d3c0184e237afa47029374b
|
3 |
size 43201
|
replay.mp4
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 sha256:0cbc1434a9235268948ac64b1d4f56521c8f30157059aacad5db81db1baed287
|
3 |
+
size 199190
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": -119.23161434091453, "std_reward": 38.93846655460916, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T08:27:21.734888"}
|