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 +24 -24
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +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: 254.42 +/- 16.17
|
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 0x7fb534f93560>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb534f935f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb534f93680>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb534f93710>", "_build": "<function ActorCriticPolicy._build at 0x7fb534f937a0>", "forward": "<function ActorCriticPolicy.forward at 0x7fb534f93830>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb534f938c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb534f93950>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb534f939e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb534f93a70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb534f93b00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fb534fdf690>"}, "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": 16, "num_timesteps": 524288, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1667591022758316808, "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": -0.04857599999999995, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 160, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.7.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "GPU Enabled": "False", "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 0x7f2e83104cb0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2e83104d40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2e83104dd0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2e83104e60>", "_build": "<function ActorCriticPolicy._build at 0x7f2e83104ef0>", "forward": "<function ActorCriticPolicy.forward at 0x7f2e83104f80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2e8310b050>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2e8310b0e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2e8310b170>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2e8310b200>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2e8310b290>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f2e831586c0>"}, "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": 1667592576474882472, "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": 155, "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": 64, "n_epochs": 5, "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-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.7.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "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:e029d8af50aa99914125d211b57d5c5c9d4de847a891c6262e54fedc4dfe3e60
|
3 |
+
size 147156
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,21 +4,21 @@
|
|
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":
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
@@ -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'>",
|
@@ -66,24 +66,24 @@
|
|
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": 2048,
|
80 |
-
"gamma": 0.
|
81 |
-
"gae_lambda": 0.
|
82 |
-
"ent_coef": 0.
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
"batch_size": 64,
|
86 |
-
"n_epochs":
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "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"
|
|
|
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 0x7f2e83104cb0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2e83104d40>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2e83104dd0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2e83104e60>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f2e83104ef0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f2e83104f80>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2e8310b050>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f2e8310b0e0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2e8310b170>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2e8310b200>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2e8310b290>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f2e831586c0>"
|
20 |
},
|
21 |
+
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1667592576474882472,
|
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": -0.015808000000000044,
|
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": 155,
|
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": 64,
|
86 |
+
"n_epochs": 5,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "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"
|
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 sha256:52b926883edd744b4dac2da619eaf5cd68bb57f4b170931ef5dde7cd61672631
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:011124dc9647953f2aae2608481acec240db4c6b995c545a31091e4a397599ab
|
3 |
+
size 43201
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -2,6 +2,6 @@ OS: Linux-5.10.133+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Fri Aug 26 08:44:51 U
|
|
2 |
Python: 3.7.15
|
3 |
Stable-Baselines3: 1.6.2
|
4 |
PyTorch: 1.12.1+cu113
|
5 |
-
GPU Enabled:
|
6 |
Numpy: 1.21.6
|
7 |
Gym: 0.21.0
|
|
|
2 |
Python: 3.7.15
|
3 |
Stable-Baselines3: 1.6.2
|
4 |
PyTorch: 1.12.1+cu113
|
5 |
+
GPU Enabled: True
|
6 |
Numpy: 1.21.6
|
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": 254.41723236553207, "std_reward": 16.168225318814972, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-04T20:29:17.269698"}
|