Trained PPO Lunar-Lander-v2
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
- 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: 283.66 +/- 18.96
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x152a72950>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x152a729e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x152a72a70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x152a72b00>", "_build": "<function ActorCriticPolicy._build at 0x152a72b90>", "forward": "<function ActorCriticPolicy.forward at 0x152a72c20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x152a72cb0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x152a72d40>", "_predict": "<function ActorCriticPolicy._predict at 0x152a72dd0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x152a72e60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x152a72ef0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x152a72f80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x152a78fc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1712946417637551000, "learning_rate": 0.0003, "tensorboard_log": null, "_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, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 310, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "macOS-14.1.1-arm64-arm-64bit Darwin Kernel Version 23.1.0: Mon Oct 9 21:27:24 PDT 2023; root:xnu-10002.41.9~6/RELEASE_ARM64_T6000", "Python": "3.10.14", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.2", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}
|
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x1223728c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x122372950>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1223729e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x122372a70>", "_build": "<function ActorCriticPolicy._build at 0x122372b00>", "forward": "<function ActorCriticPolicy.forward at 0x122372b90>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x122372c20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x122372cb0>", "_predict": "<function ActorCriticPolicy._predict at 0x122372d40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x122372dd0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x122372e60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x122372ef0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x1223789c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2031616, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1712947694395399000, "learning_rate": 0.0003, "tensorboard_log": null, "_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, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 620, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "macOS-14.1.1-arm64-arm-64bit Darwin Kernel Version 23.1.0: Mon Oct 9 21:27:24 PDT 2023; root:xnu-10002.41.9~6/RELEASE_ARM64_T6000", "Python": "3.10.14", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.2", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}
|
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 sha256:428a4b46e25acab58eab08b02702817fc7c575cf7722f566eb284ef5c7df514d
|
3 |
+
size 147552
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,34 +4,34 @@
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -45,13 +45,13 @@
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"n_steps": 2048,
|
56 |
"gamma": 0.99,
|
57 |
"gae_lambda": 0.95,
|
|
|
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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x1223728c0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x122372950>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1223729e0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x122372a70>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x122372b00>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x122372b90>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x122372c20>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x122372cb0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x122372d40>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x122372dd0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x122372e60>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x122372ef0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x1223789c0>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 2031616,
|
25 |
+
"_total_timesteps": 2000000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1712947694395399000,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 620,
|
55 |
"n_steps": 2048,
|
56 |
"gamma": 0.99,
|
57 |
"gae_lambda": 0.95,
|
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 87978
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4afcb52d962b7422660b59039e59c97ca832797985c3310a620faed9ab0aff6
|
3 |
size 87978
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43634
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e247375c962b29b46f7ed43000c198ed980a2eecd5565d3a00926447107560dc
|
3 |
size 43634
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 283.65769977717116, "std_reward": 18.96313477472105, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-12T21:57:52.090091"}
|