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 +23 -23
- 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: 292.63 +/- 22.17
|
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 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 0x7f51c6f7f670>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f51c6f7f700>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f51c6f7f790>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f51c6f7f820>", "_build": "<function ActorCriticPolicy._build at 0x7f51c6f7f8b0>", "forward": "<function ActorCriticPolicy.forward at 0x7f51c6f7f940>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f51c6f7f9d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f51c6f7fa60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f51c6f7faf0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f51c6f7fb80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f51c6f7fc10>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f51c6f76c60>"}, "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": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670707999858142442, "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": 252, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "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 0x7fb5bdac5a60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb5bdac5af0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb5bdac5b80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb5bdac5c10>", "_build": "<function ActorCriticPolicy._build at 0x7fb5bdac5ca0>", "forward": "<function ActorCriticPolicy.forward at 0x7fb5bdac5d30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb5bdac5dc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb5bdac5e50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb5bdac5ee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb5bdac5f70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb5bdaca040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fb5bdac3480>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 50003968, "_total_timesteps": 50000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671098673135392524, "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": -7.935999999997279e-05, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 12208, "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": 128, "n_epochs": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "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:feeffba87b24da434721c4cc201b46291c2970df7495c46d84e8a906e1702aa7
|
3 |
+
size 147316
|
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'>",
|
@@ -66,27 +66,27 @@
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": -
|
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":
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
-
"batch_size":
|
86 |
-
"n_epochs":
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
-
":serialized:": "
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
|
|
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 0x7fb5bdac5a60>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb5bdac5af0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb5bdac5b80>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb5bdac5c10>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fb5bdac5ca0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fb5bdac5d30>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb5bdac5dc0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fb5bdac5e50>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb5bdac5ee0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb5bdac5f70>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb5bdaca040>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fb5bdac3480>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 50003968,
|
46 |
+
"_total_timesteps": 50000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1671098673135392524,
|
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": -7.935999999997279e-05,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "gAWVHxAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIILjKEwhSckCUhpRSlIwBbJRLiIwBdJRHQNrSr1Tzd1x1fZQoaAZoCWgPQwjsLlBSoKxyQJSGlFKUaBVLvWgWR0Da0rAX1rZbdX2UKGgGaAloD0MIP+JXrGFAckCUhpRSlGgVS4doFkdA2tKyV1Oj7HV9lChoBmgJaA9DCCeDo+TVonFAlIaUUpRoFUuEaBZHQNrStydjG1h1fZQoaAZoCWgPQwhZTGw+bsFyQJSGlFKUaBVLl2gWR0Da0riAQQMAdX2UKGgGaAloD0MIMZV+wplXc0CUhpRSlGgVS5VoFkdA2tK/PfKp1nV9lChoBmgJaA9DCEMglzhyRXRAlIaUUpRoFUvDaBZHQNrSwc45tFd1fZQoaAZoCWgPQwioyCHiJqdwQJSGlFKUaBVLnWgWR0Da0sKoOx0NdX2UKGgGaAloD0MIrkm3JbKFc0CUhpRSlGgVS7poFkdA2tLTbXYlIHV9lChoBmgJaA9DCFK2SNoNE3JAlIaUUpRoFUuwaBZHQNrS1KdhAnl1fZQoaAZoCWgPQwjoobYNoydxQJSGlFKUaBVLoGgWR0Da0tWV9nbqdX2UKGgGaAloD0MIXaW762x+c0CUhpRSlGgVS7loFkdA2tLYwVCXyHV9lChoBmgJaA9DCC6PNSMDeXFAlIaUUpRoFUuuaBZHQNrS2w1vVEx1fZQoaAZoCWgPQwjW5ZSAGJVyQJSGlFKUaBVLrGgWR0Da0tukVN5/dX2UKGgGaAloD0MIzHucacI8c0CUhpRSlGgVS59oFkdA2tLcenQ6ZHV9lChoBmgJaA9DCJhPVgxX5XJAlIaUUpRoFUuwaBZHQNrS4EcsDnx1fZQoaAZoCWgPQwg51VqYRUBzQJSGlFKUaBVLs2gWR0Da0uRKcurZdX2UKGgGaAloD0MIisqGNZWVcUCUhpRSlGgVS41oFkdA2tLnQQtjC3V9lChoBmgJaA9DCOVC5V/LMnNAlIaUUpRoFUusaBZHQNrS6PN7jT91fZQoaAZoCWgPQwiE86ljFRxnQJSGlFKUaBVN6ANoFkdA2tLpQDV6NXV9lChoBmgJaA9DCLwFEhQ/HnJAlIaUUpRoFUvCaBZHQNrS7LdrO7h1fZQoaAZoCWgPQwiBBTBloAV0QJSGlFKUaBVLpGgWR0Da0u61Cw8odX2UKGgGaAloD0MI9Q63Q4MOc0CUhpRSlGgVS69oFkdA2tLxs6q82HV9lChoBmgJaA9DCFvOpbiqGnJAlIaUUpRoFUuEaBZHQNrS9e3DvVp1fZQoaAZoCWgPQwhbYfpeg4lwQJSGlFKUaBVLlGgWR0Da0vouL740dX2UKGgGaAloD0MIVd0jm6vncECUhpRSlGgVS5poFkdA2tL9/gzguXV9lChoBmgJaA9DCFaZKa1/JHRAlIaUUpRoFUuwaBZHQNrS/vv4M4N1fZQoaAZoCWgPQwhPXfksT/JvQJSGlFKUaBVLkGgWR0Da0wH50r9VdX2UKGgGaAloD0MIYhIu5BFMckCUhpRSlGgVS59oFkdA2tMCNu+AVnV9lChoBmgJaA9DCD9YxobutnBAlIaUUpRoFUujaBZHQNrTAnbEgnt1fZQoaAZoCWgPQwjG3osv2oBzQJSGlFKUaBVLs2gWR0Da0wWJ79hrdX2UKGgGaAloD0MI5usy/CfjcUCUhpRSlGgVS6FoFkdA2tMLkAPuonV9lChoBmgJaA9DCB/WG7VC/XJAlIaUUpRoFUuxaBZHQNrTDMafjCJ1fZQoaAZoCWgPQwj7sUl+BB50QJSGlFKUaBVLomgWR0Da0w1oysS1dX2UKGgGaAloD0MIbjMV4tE9ckCUhpRSlGgVS6JoFkdA2tMQ4YaYNXV9lChoBmgJaA9DCOHvF7MloHJAlIaUUpRoFUu5aBZHQNrTEkJng511fZQoaAZoCWgPQwhMUplizudzQJSGlFKUaBVLrWgWR0Da0xVruYx+dX2UKGgGaAloD0MI5UNQNXrSZUCUhpRSlGgVTegDaBZHQNrTF0KVpsZ1fZQoaAZoCWgPQwgb8WQ3s65zQJSGlFKUaBVLuGgWR0Da0xrbypaSdX2UKGgGaAloD0MI+HE0RxZLc0CUhpRSlGgVS7JoFkdA2tMdsrd30XV9lChoBmgJaA9DCIXpew0BMHFAlIaUUpRoFUuqaBZHQNrTICQcPvt1fZQoaAZoCWgPQwjwwADCh/BzQJSGlFKUaBVLqWgWR0Da0yODIzWPdX2UKGgGaAloD0MIA5Xx73OXckCUhpRSlGgVS7ZoFkdA2tMnSkTHsHV9lChoBmgJaA9DCHgI46fxt3JAlIaUUpRoFUuwaBZHQNrTKVLJ0XB1fZQoaAZoCWgPQwhSKAtfX2FzQJSGlFKUaBVLtGgWR0Da0yoGorFwdX2UKGgGaAloD0MI0qjAyXbSc0CUhpRSlGgVS8VoFkdA2tMteU6gd3V9lChoBmgJaA9DCG6I8ZqXd3JAlIaUUpRoFUunaBZHQNrTMEYj0MB1fZQoaAZoCWgPQwiY++QoQJNxQJSGlFKUaBVLrmgWR0Da0zMLQXyidX2UKGgGaAloD0MI31D4bB0Kc0CUhpRSlGgVS4xoFkdA2tM0HwPRRnV9lChoBmgJaA9DCPlOzHrx53NAlIaUUpRoFUujaBZHQNrTNM4DLbJ1fZQoaAZoCWgPQwhAhLhy9ph0QJSGlFKUaBVL2mgWR0Da0zWx8lXzdX2UKGgGaAloD0MINPJ5xZMXc0CUhpRSlGgVS8FoFkdA2tM3yprDZXV9lChoBmgJaA9DCMHEH0Vd4HNAlIaUUpRoFUu6aBZHQNrTOs6/7BR1fZQoaAZoCWgPQwh9JCU9DMJwQJSGlFKUaBVLnGgWR0Da0zyYXwb3dX2UKGgGaAloD0MI04OCUvTkc0CUhpRSlGgVS79oFkdA2tNATQVsUXV9lChoBmgJaA9DCGUcI9kjAnNAlIaUUpRoFUumaBZHQNrTQUvwmVt1fZQoaAZoCWgPQwhZNQhzOyNyQJSGlFKUaBVLomgWR0Da00KzollcdX2UKGgGaAloD0MITwRxHs6ZcUCUhpRSlGgVS4poFkdA2tNGO1fE43V9lChoBmgJaA9DCPz89+A1iHJAlIaUUpRoFUu7aBZHQNrTSvrSmZV1fZQoaAZoCWgPQwj/A6xVuxxMQJSGlFKUaBVLb2gWR0Da00xKRMewdX2UKGgGaAloD0MIYkz6e6meckCUhpRSlGgVS5ZoFkdA2tNM1yvLYHV9lChoBmgJaA9DCKaZ7nXS73FAlIaUUpRoFUu6aBZHQNrTTofGMn91fZQoaAZoCWgPQwi46c9+5ERzQJSGlFKUaBVLsWgWR0Da0084//vOdX2UKGgGaAloD0MI/KawUsHEc0CUhpRSlGgVS6RoFkdA2tNU/m1YyXV9lChoBmgJaA9DCNswCoIHkXJAlIaUUpRoFUunaBZHQNrTVqjrRjV1fZQoaAZoCWgPQwglrfiGAvVzQJSGlFKUaBVLqWgWR0Da01rcclw+dX2UKGgGaAloD0MISnuDL4yqcUCUhpRSlGgVS5ZoFkdA2tNb+0PYnXV9lChoBmgJaA9DCBVUVP0K8XJAlIaUUpRoFUu9aBZHQNrTXDodMkB1fZQoaAZoCWgPQwiJXHAGf5pzQJSGlFKUaBVL1mgWR0Da011jBl+WdX2UKGgGaAloD0MIPzc0ZecDc0CUhpRSlGgVS65oFkdA2tNmR5C4SnV9lChoBmgJaA9DCHtq9dUVznJAlIaUUpRoFUu3aBZHQNrTZzXWe6J1fZQoaAZoCWgPQwg6AyMv63ZwQJSGlFKUaBVLp2gWR0Da02pJRO1wdX2UKGgGaAloD0MI4C77daeQc0CUhpRSlGgVS+JoFkdA2tNqu5SWJXV9lChoBmgJaA9DCI3ttaD3pnRAlIaUUpRoFUvBaBZHQNrTbA3kxRF1fZQoaAZoCWgPQwhuhbAaCyhzQJSGlFKUaBVLn2gWR0Da021wn6VMdX2UKGgGaAloD0MIW3heKjZkc0CUhpRSlGgVS6poFkdA2tNxWkrPMXV9lChoBmgJaA9DCOif4GIFSnJAlIaUUpRoFUujaBZHQNrTcYZhrnF1fZQoaAZoCWgPQwhtAaH1sE1zQJSGlFKUaBVLr2gWR0Da03HsAvL6dX2UKGgGaAloD0MI9b7xtecWdECUhpRSlGgVS7toFkdA2tN25Rjz7XV9lChoBmgJaA9DCCbGMv1S2XFAlIaUUpRoFUucaBZHQNrTd9u+AVh1fZQoaAZoCWgPQwgipdk8zgByQJSGlFKUaBVLqWgWR0Da03jlOoHcdX2UKGgGaAloD0MIQNmUKzwDckCUhpRSlGgVS4poFkdA2tN5MfigkHV9lChoBmgJaA9DCGk6OxkcLXFAlIaUUpRoFUuiaBZHQNrTfv3N9ph1fZQoaAZoCWgPQwgKaY1Bp7RyQJSGlFKUaBVLs2gWR0Da04BDF6zFdX2UKGgGaAloD0MIR3U6kLUjdECUhpRSlGgVS7FoFkdA2tOA3y7PIHV9lChoBmgJaA9DCPol4q3zlXJAlIaUUpRoFUufaBZHQNrTh6f8Mux1fZQoaAZoCWgPQwhCz2bVZ6xxQJSGlFKUaBVLpmgWR0Da04hKDkELdX2UKGgGaAloD0MI14hgHNzicECUhpRSlGgVS5poFkdA2tOJoMKCx3V9lChoBmgJaA9DCOjB3Vk7X3BAlIaUUpRoFUuGaBZHQNrTjUAPuoh1fZQoaAZoCWgPQwj3V4/71plzQJSGlFKUaBVLqmgWR0Da047k92X+dX2UKGgGaAloD0MI5sx2hX7Uc0CUhpRSlGgVS8RoFkdA2tOTLiMo+nV9lChoBmgJaA9DCPYNTG5UKnRAlIaUUpRoFUvEaBZHQNrTldgjQiR1fZQoaAZoCWgPQwgriIGuvWJyQJSGlFKUaBVLsmgWR0Da05Yq5LAYdX2UKGgGaAloD0MIHAdeLfdvckCUhpRSlGgVS5FoFkdA2tOXJZ4fOnV9lChoBmgJaA9DCFkZjXxeKnRAlIaUUpRoFUu9aBZHQNrTmHocJdB1fZQoaAZoCWgPQwi4HRoWY6dyQJSGlFKUaBVLm2gWR0Da05lqEeySdX2UKGgGaAloD0MICD4GK054cUCUhpRSlGgVS6xoFkdA2tOacmShanV9lChoBmgJaA9DCPbuj/cqAnRAlIaUUpRoFUuraBZHQNrTmy5AhSt1fZQoaAZoCWgPQwjChNGs7KlyQJSGlFKUaBVLmmgWR0Da05+nGbTddX2UKGgGaAloD0MIymyQSUa4bkCUhpRSlGgVS6FoFkdA2tOf56t1ZHVlLg=="
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 12208,
|
79 |
+
"n_steps": 2048,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 128,
|
86 |
+
"n_epochs": 8,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "gAWVCQMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMay9ob21lL2JvcmlzLnVzdHl1Z292L21pbmljb25kYTMvZW52cy9kZWVwX3JsL2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCBAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxrL2hvbWUvYm9yaXMudXN0eXVnb3YvbWluaWNvbmRhMy9lbnZzL2RlZXBfcmwvbGliL3B5dGhvbjMuMTAvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
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 sha256:3ccfe318515052333378d21b7cd7643b0429bf1d88020a52d64c90b1cf8bf3ae
|
3 |
+
size 88057
|
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 sha256:78e62e2b6fa39bac60c255b9ab28629c8bf94571859f9293008c7086310b6a88
|
3 |
size 43201
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 292.63394271302184, "std_reward": 22.17033780914637, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-16T13:09:11.688203"}
|