Upload PPO LunarLander-v2
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +18 -18
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/policy.pth +1 -1
- ppo-LunarLander-v2/system_info.txt +4 -4
- replay.mp4 +0 -0
- 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: 252.75 +/- 15.81
|
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 0x7f2185899560>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f21858995f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2185899680>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2185899710>", "_build": "<function ActorCriticPolicy._build at 0x7f21858997a0>", "forward": "<function ActorCriticPolicy.forward at 0x7f2185899830>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f21858998c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2185899950>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f21858999e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2185899a70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2185899b00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f21858e87b0>"}, "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": 1658943417.257757, "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": 372, "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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.6.0", "PyTorch": "1.12.0+cu113", "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 0x7f8461498940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f84614989d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8461498a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8461498af0>", "_build": "<function ActorCriticPolicy._build at 0x7f8461498b80>", "forward": "<function ActorCriticPolicy.forward at 0x7f8461498c10>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8461498ca0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8461498d30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8461498dc0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8461498e50>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8461498ee0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f8461a49480>"}, "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": 1659665560.5138562, "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": 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, "system_info": {"OS": "Linux-5.10.102.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 #1 SMP Wed Mar 2 00:30:59 UTC 2022", "Python": "3.9.12", "Stable-Baselines3": "1.6.0", "PyTorch": "1.12.0+cu102", "GPU Enabled": "True", "Numpy": "1.23.1", "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 sha256:7e643cb76e878c04743dde6776db50011eb004739d6342eeb902fe00f110c240
|
3 |
+
size 147310
|
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": {},
|
@@ -47,16 +47,16 @@
|
|
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": {
|
54 |
":type:": "<class 'function'>",
|
55 |
-
":serialized:": "
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -69,13 +69,13 @@
|
|
69 |
"_current_progress_remaining": -0.015808000000000044,
|
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,
|
@@ -86,7 +86,7 @@
|
|
86 |
"n_epochs": 4,
|
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 0x7f8461498940>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f84614989d0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8461498a60>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8461498af0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f8461498b80>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f8461498c10>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8461498ca0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f8461498d30>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8461498dc0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8461498e50>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8461498ee0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f8461a49480>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1659665560.5138562,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
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'>",
|
|
|
69 |
"_current_progress_remaining": -0.015808000000000044,
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "gAWVgBAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIlkG1wQn+ZUCUhpRSlIwBbJRN6AOMAXSUR0CU9uCaJAMVdX2UKGgGaAloD0MIwcdgxam/ZUCUhpRSlGgVTegDaBZHQJT4gVN5+ph1fZQoaAZoCWgPQwiIu3oVGSpjQJSGlFKUaBVN6ANoFkdAlPj8ySFGonV9lChoBmgJaA9DCEBtVKeDjGNAlIaUUpRoFU3oA2gWR0CU+7rBj4HpdX2UKGgGaAloD0MIeeblsHseYkCUhpRSlGgVTegDaBZHQJT91LwnYxt1fZQoaAZoCWgPQwhBvK5fsPJmQJSGlFKUaBVN6ANoFkdAlP/rmITGpHV9lChoBmgJaA9DCIbGE0Ec5WBAlIaUUpRoFU3oA2gWR0CVAkCDEm6YdX2UKGgGaAloD0MIsd6oFaYQZ0CUhpRSlGgVTegDaBZHQJUIpomG/N91fZQoaAZoCWgPQwhJSnoYWuVFQJSGlFKUaBVL9WgWR0CVCcicG1QZdX2UKGgGaAloD0MIVIzzN6EPZECUhpRSlGgVTegDaBZHQJUM8LQXyiF1fZQoaAZoCWgPQwhkXdxGg1tjQJSGlFKUaBVN6ANoFkdAlRHyWNWEK3V9lChoBmgJaA9DCLCMDd1skG9AlIaUUpRoFU2WA2gWR0CVHFZHuqm1dX2UKGgGaAloD0MIHCPZI9TJZUCUhpRSlGgVTegDaBZHQJUidgfEGaB1fZQoaAZoCWgPQwh6Oey+41JkQJSGlFKUaBVN6ANoFkdAlUzFrdnCf3V9lChoBmgJaA9DCJGcTNwqTmVAlIaUUpRoFU3oA2gWR0CVTv4tYjjadX2UKGgGaAloD0MIjnbc8LuKYUCUhpRSlGgVTegDaBZHQJVPNOXVsk91fZQoaAZoCWgPQwg0nZ0MjrFjQJSGlFKUaBVN6ANoFkdAlVfOearmyXV9lChoBmgJaA9DCHeHFAOkbWJAlIaUUpRoFU3oA2gWR0CVWGtfoicHdX2UKGgGaAloD0MIQmDl0KLuYECUhpRSlGgVTegDaBZHQJVaDevZAY51fZQoaAZoCWgPQwjRzf5AuRNkQJSGlFKUaBVN6ANoFkdAlVqNB4Uvf3V9lChoBmgJaA9DCEG2LF+XrmZAlIaUUpRoFU3oA2gWR0CVX6K2rn1WdX2UKGgGaAloD0MIlXzsLlBLZkCUhpRSlGgVTegDaBZHQJVh3GR3eN11fZQoaAZoCWgPQwjyKJXwBDloQJSGlFKUaBVN6ANoFkdAlWQ8Of/WD3V9lChoBmgJaA9DCJNX5xiQFTtAlIaUUpRoFU0KAWgWR0CVZ4by6MBIdX2UKGgGaAloD0MIpIriVdatYkCUhpRSlGgVTegDaBZHQJVqevRqoIh1fZQoaAZoCWgPQwiXrmAb8etnQJSGlFKUaBVN6ANoFkdAlWuJwGW2PXV9lChoBmgJaA9DCDFfXoD9kmRAlIaUUpRoFU3oA2gWR0CVblVM23rldX2UKGgGaAloD0MIByeiX1sVYUCUhpRSlGgVTegDaBZHQJVyz4fwI+p1fZQoaAZoCWgPQwibyTfb3C5jQJSGlFKUaBVN6ANoFkdAlXyU4R28qXV9lChoBmgJaA9DCKrzqPg/gmJAlIaUUpRoFU3oA2gWR0CVgligkC3gdX2UKGgGaAloD0MIoffGEAApXkCUhpRSlGgVTegDaBZHQJWJvMKTjed1fZQoaAZoCWgPQwjfcB+5NThkQJSGlFKUaBVN6ANoFkdAla6jsMRYinV9lChoBmgJaA9DCH45s12hXV9AlIaUUpRoFU3oA2gWR0CVrtZbY9PldX2UKGgGaAloD0MIeJYgI6CUZUCUhpRSlGgVTegDaBZHQJW3YAZKnNx1fZQoaAZoCWgPQwiRt1z92BJnQJSGlFKUaBVN6ANoFkdAlbm4qwyIpHV9lChoBmgJaA9DCAAce/Zc8GJAlIaUUpRoFU3oA2gWR0CVuj8YyfthdX2UKGgGaAloD0MIck7sof3HY0CUhpRSlGgVTegDaBZHQJW/gGpuMuR1fZQoaAZoCWgPQwiyoZv9gYowQJSGlFKUaBVNKwFoFkdAlcDkmD15B3V9lChoBmgJaA9DCMAiv34I/mVAlIaUUpRoFU3oA2gWR0CVwb0k4WDZdX2UKGgGaAloD0MIjINLx5wtX0CUhpRSlGgVTegDaBZHQJXEBhH9WIZ1fZQoaAZoCWgPQwjiBnx+GNJnQJSGlFKUaBVN6ANoFkdAlcb7/GVAzHV9lChoBmgJaA9DCIj2sYJfOGJAlIaUUpRoFU3oA2gWR0CVybSRbKRudX2UKGgGaAloD0MIJZF9kOVkZ0CUhpRSlGgVTegDaBZHQJXKqLVFx4p1fZQoaAZoCWgPQwiDwqBMI2tgQJSGlFKUaBVN6ANoFkdAlc01lf7aZnV9lChoBmgJaA9DCDYiGAcXF2VAlIaUUpRoFU3oA2gWR0CV0XgrH2h7dX2UKGgGaAloD0MIti+gF25FYUCUhpRSlGgVTegDaBZHQJXa+BSUC7t1fZQoaAZoCWgPQwjCobd4eL9jQJSGlFKUaBVN6ANoFkdAleDZq7Ack3V9lChoBmgJaA9DCAt9sIyN/mNAlIaUUpRoFU3oA2gWR0CV6GriEQGwdX2UKGgGaAloD0MIIxCv65fAYECUhpRSlGgVTegDaBZHQJYM6T1TR6Z1fZQoaAZoCWgPQwhoQSjv45FiQJSGlFKUaBVN6ANoFkdAlhYjye7L+3V9lChoBmgJaA9DCHAIVWp2nGRAlIaUUpRoFU3oA2gWR0CWGKLfDUExdX2UKGgGaAloD0MIucX83FBbYECUhpRSlGgVTegDaBZHQJYZOxbB42V1fZQoaAZoCWgPQwg8LT9wFYxmQJSGlFKUaBVN6ANoFkdAlh7XFHavinV9lChoBmgJaA9DCE94CU79XmZAlIaUUpRoFU3oA2gWR0CWIFRpDeCTdX2UKGgGaAloD0MIsyeBzTnnZUCUhpRSlGgVTegDaBZHQJYhONo8IRh1fZQoaAZoCWgPQwibdjHNdMRZQJSGlFKUaBVN6ANoFkdAliOY4yXUpnV9lChoBmgJaA9DCFuaWyGsi2FAlIaUUpRoFU3oA2gWR0CWJsaEi+tbdX2UKGgGaAloD0MIGqTgKWStY0CUhpRSlGgVTegDaBZHQJYpgcU/OdJ1fZQoaAZoCWgPQwjPhZFe1CRaQJSGlFKUaBVN6ANoFkdAlip/kJa7mXV9lChoBmgJaA9DCCvCTUYV+mFAlIaUUpRoFU3oA2gWR0CWLRhG6PKddX2UKGgGaAloD0MIQwQcQhUnZECUhpRSlGgVTegDaBZHQJYxbtnf2sd1fZQoaAZoCWgPQwjdQlcikBRzQJSGlFKUaBVNowFoFkdAljgqoQ4CIXV9lChoBmgJaA9DCL4XX7THEV9AlIaUUpRoFU3oA2gWR0CWOzyPuG9IdX2UKGgGaAloD0MInbtdL01xRECUhpRSlGgVTQ0BaBZHQJY9MZuQ6p51fZQoaAZoCWgPQwiAngYMkpRfQJSGlFKUaBVN6ANoFkdAlkCwYgq3E3V9lChoBmgJaA9DCNZyZyYYN2JAlIaUUpRoFU3oA2gWR0CWR3hKlHjIdX2UKGgGaAloD0MIw/S9hmDWYkCUhpRSlGgVTegDaBZHQJZJeGoJiRZ1fZQoaAZoCWgPQwhU/yCSIaphQJSGlFKUaBVN6ANoFkdAlnSjv3JxN3V9lChoBmgJaA9DCLVSCOQS+1hAlIaUUpRoFU3oA2gWR0CWdwnBciW3dX2UKGgGaAloD0MIWd5VDxh2YECUhpRSlGgVTegDaBZHQJZ3mHymQ8x1fZQoaAZoCWgPQwjw+zcvzuBjQJSGlFKUaBVN6ANoFkdAln0CmqHXVnV9lChoBmgJaA9DCIOHad9cCmVAlIaUUpRoFU3oA2gWR0CWf1HOryUcdX2UKGgGaAloD0MIxRouck90ZECUhpRSlGgVTegDaBZHQJaBrollbvB1fZQoaAZoCWgPQwi+3CdHgcdmQJSGlFKUaBVN6ANoFkdAloTEOiFj/nV9lChoBmgJaA9DCBKhEWxcVGVAlIaUUpRoFU3oA2gWR0CWh5FnqVyFdX2UKGgGaAloD0MI6l4n9WUFYkCUhpRSlGgVTegDaBZHQJaIj6Q/5cl1fZQoaAZoCWgPQwhgyVUsfrhfQJSGlFKUaBVN6ANoFkdAlo+baVUuMHV9lChoBmgJaA9DCCgqG9bU22ZAlIaUUpRoFU3oA2gWR0CWlg3r2QGOdX2UKGgGaAloD0MIaoR+pl4LQkCUhpRSlGgVTRMBaBZHQJaXNH8TBZZ1fZQoaAZoCWgPQwhIUtLDUIliQJSGlFKUaBVN6ANoFkdAlpjnQhOgx3V9lChoBmgJaA9DCJj6eVMRLmJAlIaUUpRoFU3oA2gWR0CWmr12aDwpdX2UKGgGaAloD0MIUYaqmEr7YECUhpRSlGgVTegDaBZHQJaeCSJTER91fZQoaAZoCWgPQwjB5bFmZGRdQJSGlFKUaBVN6ANoFkdAlqSCPdVNpXV9lChoBmgJaA9DCH/C2a3lq2dAlIaUUpRoFU3oA2gWR0CWplr6LwWndX2UKGgGaAloD0MIW5iFdk5zQ0CUhpRSlGgVTSYBaBZHQJbOODHwPRR1fZQoaAZoCWgPQwgsRfKVQMJjQJSGlFKUaBVN6ANoFkdAltDMMmWt2nV9lChoBmgJaA9DCLZq14Q0VWJAlIaUUpRoFU3oA2gWR0CW0vZxJd0JdX2UKGgGaAloD0MIxy5RvbWvYkCUhpRSlGgVTegDaBZHQJbTeM1jy4F1fZQoaAZoCWgPQwjd7uU+OZNaQJSGlFKUaBVN6ANoFkdAltiqG1x82XV9lChoBmgJaA9DCM3LYfedH2dAlIaUUpRoFU3oA2gWR0CW2te7L+xXdX2UKGgGaAloD0MII0kQrgC2ZUCUhpRSlGgVTegDaBZHQJbdNLbpNbl1fZQoaAZoCWgPQwivIw7ZwGtmQJSGlFKUaBVN6ANoFkdAluBeDaoMrnV9lChoBmgJaA9DCM2wUdZv32FAlIaUUpRoFU3oA2gWR0CW5DK8+RozdX2UKGgGaAloD0MI0zJS76kycUCUhpRSlGgVTToDaBZHQJbrNSl3yI51fZQoaAZoCWgPQwh64c6Fke9gQJSGlFKUaBVN6ANoFkdAluwsu8K5TnV9lChoBmgJaA9DCMgMVMY/MGRAlIaUUpRoFU3oA2gWR0CW8yxwAEMcdX2UKGgGaAloD0MIpRKe0GtiZECUhpRSlGgVTegDaBZHQJb0XAsTWXl1fZQoaAZoCWgPQwi0q5Dyk49iQJSGlFKUaBVN6ANoFkdAlvvY4Ia99XV9lChoBmgJaA9DCKcC7nn+0GRAlIaUUpRoFU3oA2gWR0CXA0jgQ6IWdX2UKGgGaAloD0MIrvAuF/HIZUCUhpRSlGgVTegDaBZHQJcFd+x4Y791ZS4="
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 248,
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
|
|
86 |
"n_epochs": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
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 87865
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0eb9400862447fde3f9354d6e8af9d4b75063ee2e2d6e1a1cd2bee48d953d75
|
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:bd2ad29e62e694e541bdc472069b8defbc6689c7f3a3240b45fd9689bd9f5b29
|
3 |
size 43201
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
OS: Linux-5.
|
2 |
-
Python: 3.
|
3 |
Stable-Baselines3: 1.6.0
|
4 |
-
PyTorch: 1.12.0+
|
5 |
GPU Enabled: True
|
6 |
-
Numpy: 1.
|
7 |
Gym: 0.21.0
|
|
|
1 |
+
OS: Linux-5.10.102.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 #1 SMP Wed Mar 2 00:30:59 UTC 2022
|
2 |
+
Python: 3.9.12
|
3 |
Stable-Baselines3: 1.6.0
|
4 |
+
PyTorch: 1.12.0+cu102
|
5 |
GPU Enabled: True
|
6 |
+
Numpy: 1.23.1
|
7 |
Gym: 0.21.0
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 252.74655328390241, "std_reward": 15.806112520932388, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-04T21:57:18.524708"}
|