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 +16 -16
- 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: 223.75 +/- 86.92
|
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 0x7c9bea289ab0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c9bea289b40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c9bea289bd0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c9bea289c60>", "_build": "<function ActorCriticPolicy._build at 0x7c9bea289cf0>", "forward": "<function ActorCriticPolicy.forward at 0x7c9bea289d80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c9bea289e10>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c9bea289ea0>", "_predict": "<function ActorCriticPolicy._predict at 0x7c9bea289f30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c9bea289fc0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c9bea28a050>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c9bea28a0e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c9bea22dd40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1725264906777640964, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAJoyQr0ptG66HLEeN6+BEzJjwxW7ieQ5tgAAgD8AAIA/zZigu2yzgLvafqA9UBwVvrb2SrzVmTG/AACAPwAAgD8aY2C9Fm11P1jmUr0+nty+SjuMvSrHFLwAAAAAAAAAADOrD7z/0m0+YDfbPQ42kb5udpY8+GRoPQAAAAAAAAAAxsNNvowdKj96G6s9vMfCvrjRJb6GpNQ8AAAAAAAAAADGBEI+4afhPhR9lL3hQqC+AUkAPXqYtbwAAAAAAAAAAGA6Fj7dMZg+wymzvhIJZr5hFpe8W0lUvQAAAAAAAAAAA52QPvpX2z589oC+ucVYvoDV9TxqlqO9AAAAAAAAAACAoY4+D873Pkqmhzzny5C+LQk2Pr2b5L0AAAAAAAAAAAAXe73f3ao/WqKsvvRN076BA/y87h77vQAAAAAAAAAAGru/va5NpbrLwFe1XOujsIMmmjkY2n00AACAPwAAgD9m2Ja8SKqAOx4qAL7D8wy+pd3xvOMqjLoAAAAAAAAAAKYaTj5WdRE/yQC7vIMVub5/ioc9DHYEPAAAAAAAAAAAhhdGvvQw1j5SFwI+pQ+qvuPtBr7kMAs+AAAAAAAAAACgYSw+YWwaP+PjcL3syJO+0lWWPRdaGL4AAAAAAAAAADMvub260bw/SuoPv5q6sLwaksk9QPyuPQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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": 248, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
|
|
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 0x7aacd3bf2320>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7aacd3bf23b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7aacd3bf2440>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7aacd3bf24d0>", "_build": "<function ActorCriticPolicy._build at 0x7aacd3bf2560>", "forward": "<function ActorCriticPolicy.forward at 0x7aacd3bf25f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7aacd3bf2680>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7aacd3bf2710>", "_predict": "<function ActorCriticPolicy._predict at 0x7aacd3bf27a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7aacd3bf2830>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7aacd3bf28c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7aacd3bf2950>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7aacd3b55a40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1725351702393635554, "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": 248, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.4.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
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:dbff8f83715413a5240a5ddbb6a793c79fd9eee28bf3f7a09eea5a71e25d601b
|
3 |
+
size 148080
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,20 +4,20 @@
|
|
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": {},
|
@@ -26,12 +26,12 @@
|
|
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'>",
|
@@ -45,7 +45,7 @@
|
|
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'>",
|
|
|
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 0x7aacd3bf2320>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7aacd3bf23b0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7aacd3bf2440>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7aacd3bf24d0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7aacd3bf2560>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7aacd3bf25f0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7aacd3bf2680>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7aacd3bf2710>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7aacd3bf27a0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7aacd3bf2830>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7aacd3bf28c0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7aacd3bf2950>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7aacd3b55a40>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1725351702393635554,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAADOrVjsCVak+en4zvUW5YL5j6Hg8LzkNPQAAAAAAAAAATSf5vVyHCbp8z4U5qkrQNXKCIjzAqaK4AACAPwAAgD/AYOm9rkWDut27VTkz1Q+1FYZQO2JhbbgAAIA/AACAP2YEiL1flyk/XaW9vXkslb5p8S88srd5PAAAAAAAAAAA2nOVvSl9RD9df1C9grW7vo+cpL1mERK9AAAAAAAAAAAzDXm89kwmuuN0JzgE6R0zJcQjOsIORLcAAIA/AACAP/Mmzb2SU4o+ojUBPukEmb617yi8tik7PQAAAAAAAAAARhQ9vogNrLzTvIq7kF4OulIxGD6I1eI6AACAPwAAgD9mHic9w2lruuAR07svbLc1mUsrum4TJrUAAIA/AACAPwBFDz3pSwu8qGHWOuz0+zwkZGu9rsPMPQAAgD8AAIA/mrMmvFxTVbq29J81MLk9MZGHqjop+KW0AACAPwAAgD+z/8m94QiXunG1gTkekG80p2mVOdr2lbgAAIA/AACAPxpGaT0URIe6A0PXOl4/FjX8n6O6e6z3uQAAgD8AAIA/jRiCvalJfz1NFa69JFeMvhKszb1uDB+9AAAAAAAAAABLxZS+QgtaPq06lj3mKjC+EJH2vXZWqD0AAAAAAAAAABpBND2FI525DwkfvPsNMjMWo6m7DmNrswAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
|
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:": "gAWVPwwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQGJPkO7QLNSMAWyUTegDjAF0lEdAkYE25H3DenV9lChoBkdAYdmDyOJcgWgHTegDaAhHQJGDZcJMQEp1fZQoaAZHQGbWpaq0dBBoB03oA2gIR0CRhB2A5JbudX2UKGgGR0BhgepyZKFqaAdN6ANoCEdAkYRBJ7LMcXV9lChoBkdAZRcUs4DLbGgHTegDaAhHQJGJoMI/qxF1fZQoaAZHQF6Z74SHuZ1oB03oA2gIR0CRm768g6ltdX2UKGgGR0BMLJ3PiT+vaAdNJgFoCEdAkZ3QwGnn+3V9lChoBkdAY5Ks189fTmgHTegDaAhHQJGesPOIInl1fZQoaAZHQGcyFUZNwitoB03oA2gIR0CRnx+z+m3wdX2UKGgGR0Bm4KUmlZX/aAdN6ANoCEdAkZ+PAj6eoXV9lChoBkdAXdU78vVVgmgHTegDaAhHQJGgr49HMEB1fZQoaAZHQGI/8e0Xxe9oB03oA2gIR0CRoNIq9XcQdX2UKGgGR0Bi3OMMqjJuaAdN6ANoCEdAkablHvttynV9lChoBkdAYzF6X0Gu92gHTegDaAhHQJGo/x4IKMN1fZQoaAZHQGDYxB/qgRNoB03oA2gIR0CRvktPHktFdX2UKGgGR0Bfdto8IRh+aAdN6ANoCEdAkb8WD+R5knV9lChoBkdAYREeVcD8tWgHTegDaAhHQJHNQUtZmqZ1fZQoaAZHQGRT0BXCCSRoB03oA2gIR0CRzuitq59WdX2UKGgGR0BkR2+AVfu1aAdN6ANoCEdAkc90ZrHlwXV9lChoBkdAZBAOpbUwz2gHTegDaAhHQJHPjMQmNR51fZQoaAZHQHCoLMgU1yhoB03zAmgIR0CR0pKoybhFdX2UKGgGR0Bj3NSwW3z+aAdN6ANoCEdAkdRfK2a2F3V9lChoBkdAZAr7VJ+UhWgHTegDaAhHQJHVfJW/8EV1fZQoaAZHQGQk1ObiIcloB03oA2gIR0CR6nBNVR1pdX2UKGgGR0Bij/X/YJ3QaAdN6ANoCEdAkesbJbMX8HV9lChoBkdAY/xI5HVf/mgHTegDaAhHQJHrd+z+m3x1fZQoaAZHQGZXvCdjG1hoB03oA2gIR0CR69bGm1pkdX2UKGgGR0BkH1CAtnPFaAdN6ANoCEdAkeyNS/CZW3V9lChoBkdAYxxat9x6wGgHTegDaAhHQJHsonCwbER1fZQoaAZHQGdhjMFEAo5oB03oA2gIR0CR8WJlrdnCdX2UKGgGR0Bv4X2oNutPaAdNiwFoCEdAkf0hF3IMjXV9lChoBkdAY1O9JSR8t2gHTegDaAhHQJIFkZccENh1fZQoaAZHQGHM2Kl54W1oB03oA2gIR0CSBowFkhA4dX2UKGgGR0BmIEaya/h3aAdN6ANoCEdAkhePsqril3V9lChoBkdAZbf5nDiwS2gHTegDaAhHQJIZdISUTtd1fZQoaAZHQGba3k5p8F9oB03oA2gIR0CSGiWbPQfIdX2UKGgGR0BwJLTYukDZaAdN5wNoCEdAkho3Mpw0f3V9lChoBkdAZXiKPXCj12gHTegDaAhHQJId32RJVbR1fZQoaAZHQGQU3P7el9BoB03oA2gIR0CSH3axHG0edX2UKGgGR0BnJBsANoalaAdN6ANoCEdAkiBkOAiFCnV9lChoBkdAXpGo/A0sOGgHTegDaAhHQJIzsZEUj9p1fZQoaAZHQGKfOkDZDiRoB03oA2gIR0CSNNrFfiPydX2UKGgGR0BjE2w5eZ5SaAdN6ANoCEdAkjVNbxEv03V9lChoBkdAXoa4SYgJTmgHTegDaAhHQJI2NtBOYY11fZQoaAZHQGL0tZvDP4VoB03oA2gIR0CSNk3ztkWidX2UKGgGR0BmlAZwXIluaAdN6ANoCEdAkj2kngHeJ3V9lChoBkfAN1qzVtoBaWgHS/FoCEdAkj5dlVcUunV9lChoBkdAchmViWmgrmgHTTwBaAhHQJJJJwuM+/x1fZQoaAZHQGNRDTa0x/NoB03oA2gIR0CSS2rvsqrjdX2UKGgGR0BijSMzdk8SaAdN6ANoCEdAklKnz19ORHV9lChoBkdAY5WjOcDr7mgHTegDaAhHQJJTSpJf6XV1fZQoaAZHQGMCngHeJpFoB03oA2gIR0CSYG7eVLSNdX2UKGgGR0BmsWoDPnjiaAdN6ANoCEdAkmI615Sm7HV9lChoBkdAY3NzKcNH6WgHTegDaAhHQJJi1enhsIp1fZQoaAZHQGZ0Tm4iHIpoB03oA2gIR0CSYuSZ0CA+dX2UKGgGR0BwMmJzkp7UaAdNwgFoCEdAkmNihew9q3V9lChoBkdAYlG4z7/GVGgHTegDaAhHQJJl4SYgJTl1fZQoaAZHQGI6QCbMHKRoB03oA2gIR0CSZx+kP+XJdX2UKGgGR0BgLfQhOgxraAdN6ANoCEdAkmmaXF98Z3V9lChoBkdAY2JDlYEGJWgHTegDaAhHQJJ+SOaOPvN1fZQoaAZHQGDmf642CNFoB03oA2gIR0CSfrWxhUiqdX2UKGgGR0Bdvme6I3zdaAdN6ANoCEdAkn+gxesxPHV9lChoBkdAQnSwdKdxyWgHS9xoCEdAkoAbCSA6MnV9lChoBkdAZFxzo2XLNmgHTegDaAhHQJKFcPkJa7p1fZQoaAZHQGBCDwx33YdoB03oA2gIR0CShfI8yN4rdX2UKGgGR0BC9/sNUfgaaAdL62gIR0CSiRUEPlMidX2UKGgGR0BvXFBQemvXaAdN+AFoCEdAko3W+XZ5A3V9lChoBkdAZE+0LMLWqmgHTegDaAhHQJKOL5aePJd1fZQoaAZHQGRU0Hpr1uloB03oA2gIR0CSloc4o7V8dX2UKGgGR0BiHAxxkupTaAdN6ANoCEdAkpcv1YhdMXV9lChoBkdAcDXUoa1kUmgHTT0CaAhHQJKbqbmU4aR1fZQoaAZHv9TewcHWz4VoB0vraAhHQJKkstEofCB1fZQoaAZHQFzmKwIMSbpoB03oA2gIR0CSpwKvmozfdX2UKGgGR0BeTXzlLeyiaAdN6ANoCEdAkqktTtLL6nV9lChoBkdAbD/DJlrdnGgHTRIDaAhHQJKphBAv+Ox1fZQoaAZHQF+9acZtNztoB03oA2gIR0CSqfbSJCSidX2UKGgGR0Bv5XJA+pwTaAdNVgNoCEdAkqtk0m+j/XV9lChoBkdARPvOB19v0mgHS/5oCEdAkqwhX0XgtXV9lChoBkdAZHtOKwY+CGgHTegDaAhHQJKs3rs0HhV1fZQoaAZHQGH2rV4HHFRoB03oA2gIR0CSrfrN4Z/DdX2UKGgGR0Bve5rzoUzsaAdNZAJoCEdAkq9X09QoC3V9lChoBkdAZDDd1uBMBmgHTegDaAhHQJKwOeBg/kh1fZQoaAZHQG16EVN5+phoB039AmgIR0CSx1rd30PIdX2UKGgGR0BlQvyEtdzGaAdN6ANoCEdAksoG+j/Mn3V9lChoBkdAZByWtU4rBmgHTegDaAhHQJLKmLaVUuN1fZQoaAZHQGACUUoKD01oB03oA2gIR0CSzj62OQyRdX2UKGgGR0ByMhYnv2GqaAdN8QFoCEdAktAb9ETg23V9lChoBkdAbJH8qFyq/GgHTYUCaAhHQJLdB4Vymyh1fZQoaAZHQFjIwSJ0nw5oB03oA2gIR0CS4Zo371qWdX2UKGgGR0BymzRArxy5aAdNhAFoCEdAkuL2SZBsynV9lChoBkdAcYvona37UGgHTTsDaAhHQJLtxfShJy11fZQoaAZHQGeOF5OafBhoB03oA2gIR0CS7jn8baRIdX2UKGgGR0Bt5I3kxREXaAdNjQJoCEdAku7bjDKoynV9lChoBkdAYLTj4pMHr2gHTegDaAhHQJLxSGgzxgB1fZQoaAZHQGMEqv/zasZoB03oA2gIR0CS8dT2nKnvdX2UKGgGR0BlKZItlI3BaAdN6ANoCEdAkvMT7Q9idHV9lChoBkdAZeXgJkXk52gHTegDaAhHQJLz5WilBQh1fZQoaAZHQGREgv+OwPloB03oA2gIR0CS9Lynk1dgdX2UKGgGR0Bh0qYzBRAKaAdN6ANoCEdAkvdwJHAh0XV9lChoBkdAYUX1ie/Ya2gHTegDaAhHQJL4dMFlkH51ZS4="
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
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 88362
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cf830f3196022cb943876d2063ee806ca908f5f750244963fa6309862cf80a0
|
3 |
size 88362
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2035af598e3e8e48763be7f93df46e2bc8bb449dadd2dc25ab749cfedfe2d924
|
3 |
size 43762
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 223.74894279990696, "std_reward": 86.91606512627625, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-03T09:01:15.674993"}
|