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 +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: 265.98 +/- 18.21
|
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 0x7fc0135f3ca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc0135f3d30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc0135f3dc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc0135f3e50>", "_build": "<function ActorCriticPolicy._build at 0x7fc0135f3ee0>", "forward": "<function ActorCriticPolicy.forward at 0x7fc0135f3f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc0135f7040>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc0135f70d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc0135f7160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc0135f71f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc0135f7280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fc0135f04b0>"}, "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": 1672302715278863963, "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-5.10.133+-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 0x7ff74f9c4c10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff74f9c4ca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff74f9c4d30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff74f9c4dc0>", "_build": "<function ActorCriticPolicy._build at 0x7ff74f9c4e50>", "forward": "<function ActorCriticPolicy.forward at 0x7ff74f9c4ee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff74f9c4f70>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff74f949040>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff74f9490d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff74f949160>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff74f9491f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7ff74f9c2480>"}, "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": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1672678197880933452, "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": -0.007616000000000067, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 492, "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"}}
|
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:c0617dc887bd86cad313cbcd043823351769095d601d3ed1aed7d4a53538dabc
|
3 |
+
size 147114
|
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 0x7ff74f9c4c10>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff74f9c4ca0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff74f9c4d30>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff74f9c4dc0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7ff74f9c4e50>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7ff74f9c4ee0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff74f9c4f70>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7ff74f949040>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff74f9490d0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff74f949160>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff74f9491f0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7ff74f9c2480>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 2015232,
|
46 |
+
"_total_timesteps": 2000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1672678197880933452,
|
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": -0.007616000000000067,
|
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": 492,
|
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 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2f6f9633d117639b00e7908ed9d732b5cb264082b4f188afbc436d99e0f98f1
|
3 |
size 87929
|
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 sha256:4769410a697403b7e1c0d9411dbf75e5d385a470621d9a9a3df51c3ff8fb1366
|
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": 265.97831014493096, "std_reward": 18.20838820724976, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T17:21:05.169188"}
|