first commit
Browse files- README.md +1 -1
- config.json +1 -1
- ppo_lunarlander.zip +2 -2
- ppo_lunarlander/data +20 -20
- ppo_lunarlander/policy.optimizer.pth +1 -1
- ppo_lunarlander/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: 271.74 +/- 14.75
|
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 0x7f3c685931f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3c68593280>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3c68593310>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3c685933a0>", "_build": "<function ActorCriticPolicy._build at 0x7f3c68593430>", "forward": "<function ActorCriticPolicy.forward at 0x7f3c685934c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3c68593550>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3c685935e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3c68593670>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3c68593700>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3c68593790>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3c68593820>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f3c68587e70>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 114688, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1673856161374585070, "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": -0.1468799999999999, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 28, "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-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.7.0", "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 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 0x7f5a76903790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5a76903820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5a769038b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5a76903940>", "_build": "<function ActorCriticPolicy._build at 0x7f5a769039d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f5a76903a60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5a76903af0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5a76903b80>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5a76903c10>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5a76903ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5a76903d30>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5a76903dc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f5a768fd960>"}, "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": 1673860862374882323, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo_lunarlander.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:e6e1999f3e279a49ff86dbba8369ef38949b1cadd8c10f42d4da0dde21b48bf5
|
3 |
+
size 147420
|
ppo_lunarlander/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_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
@@ -43,12 +43,12 @@
|
|
43 |
"_np_random": null
|
44 |
},
|
45 |
"n_envs": 16,
|
46 |
-
"num_timesteps":
|
47 |
-
"_total_timesteps":
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
-
"start_time":
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
@@ -57,7 +57,7 @@
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
-
":serialized:": "
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -67,16 +67,16 @@
|
|
67 |
"_episode_num": 0,
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
-
"_current_progress_remaining": -0.
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
-
":serialized:": "
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
-
"_n_updates":
|
80 |
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"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 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 0x7f5a76903790>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5a76903820>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5a769038b0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5a76903940>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f5a769039d0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f5a76903a60>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5a76903af0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5a76903b80>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f5a76903c10>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5a76903ca0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5a76903d30>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5a76903dc0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc_data object at 0x7f5a768fd960>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
43 |
"_np_random": null
|
44 |
},
|
45 |
"n_envs": 16,
|
46 |
+
"num_timesteps": 1015808,
|
47 |
+
"_total_timesteps": 1000000,
|
48 |
"_num_timesteps_at_start": 0,
|
49 |
"seed": null,
|
50 |
"action_noise": null,
|
51 |
+
"start_time": 1673860862374882323,
|
52 |
"learning_rate": 0.0003,
|
53 |
"tensorboard_log": null,
|
54 |
"lr_schedule": {
|
|
|
57 |
},
|
58 |
"_last_obs": {
|
59 |
":type:": "<class 'numpy.ndarray'>",
|
60 |
+
":serialized:": "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"
|
61 |
},
|
62 |
"_last_episode_starts": {
|
63 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
67 |
"_episode_num": 0,
|
68 |
"use_sde": false,
|
69 |
"sde_sample_freq": -1,
|
70 |
+
"_current_progress_remaining": -0.015808000000000044,
|
71 |
"ep_info_buffer": {
|
72 |
":type:": "<class 'collections.deque'>",
|
73 |
+
":serialized:": "gAWVfhAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIRGraxTTLNkCUhpRSlIwBbJRL54wBdJRHQI94zedkJ8h1fZQoaAZoCWgPQwj9aDhlbsFgQJSGlFKUaBVN6ANoFkdAj3+buMMqjXV9lChoBmgJaA9DCE/mH32T0GZAlIaUUpRoFU3oA2gWR0CPiCgctGutdX2UKGgGaAloD0MI3pOHhdqpYkCUhpRSlGgVTegDaBZHQI+ObTz/ZNB1fZQoaAZoCWgPQwijW6/pQexkQJSGlFKUaBVN6ANoFkdAj5DFcY64lXV9lChoBmgJaA9DCOM1r+qsG2JAlIaUUpRoFU3oA2gWR0CPm2gq3EyddX2UKGgGaAloD0MIwqG3eHirZkCUhpRSlGgVTegDaBZHQI+c1JQLux91fZQoaAZoCWgPQwi5xmeyf49dQJSGlFKUaBVN6ANoFkdAj6BHeaa1C3V9lChoBmgJaA9DCFLuPsfHuGNAlIaUUpRoFU3oA2gWR0CPpEnw5NoKdX2UKGgGaAloD0MIGeYEbfI6ZkCUhpRSlGgVTegDaBZHQI+pCYmb9ZR1fZQoaAZoCWgPQwjB4Jo7+iM/QJSGlFKUaBVL0GgWR0CPtSjXWe6JdX2UKGgGaAloD0MI6QyMvKx7YkCUhpRSlGgVTegDaBZHQI+53NNahYh1fZQoaAZoCWgPQwg+527XSzhlQJSGlFKUaBVN6ANoFkdAj8B3d0q6OHV9lChoBmgJaA9DCJ88LNQaJWRAlIaUUpRoFU3oA2gWR0CPwLFAE+xGdX2UKGgGaAloD0MIgSbChieJZkCUhpRSlGgVTegDaBZHQI/DlFnZkCp1fZQoaAZoCWgPQwiLUkKwqlplQJSGlFKUaBVN6ANoFkdAj9kgU+LWJHV9lChoBmgJaA9DCBniWBc3cWRAlIaUUpRoFU3oA2gWR0CQAcDujRD1dX2UKGgGaAloD0MIu9QI/cwSZECUhpRSlGgVTegDaBZHQJAElsj3VTd1fZQoaAZoCWgPQwi8zRsnhfxlQJSGlFKUaBVN6ANoFkdAkAdhPbfxc3V9lChoBmgJaA9DCFsHB3uT/GdAlIaUUpRoFU3oA2gWR0CQCubtZ3cIdX2UKGgGaAloD0MIoz1eSIfuW0CUhpRSlGgVTegDaBZHQJANlUm2LHd1fZQoaAZoCWgPQwjf/lw05G5lQJSGlFKUaBVN6ANoFkdAkA6dAs052nV9lChoBmgJaA9DCJw24zREw2NAlIaUUpRoFU3oA2gWR0CQE1k/KQq7dX2UKGgGaAloD0MIC0J5H0f2aUCUhpRSlGgVTegDaBZHQJAUAM6RyOt1fZQoaAZoCWgPQwjBcoQM5KJkQJSGlFKUaBVN6ANoFkdAkBeth/iHZnV9lChoBmgJaA9DCAZJn1ZRwHJAlIaUUpRoFU26AWgWR0CQF9de6ZpjdX2UKGgGaAloD0MI8KXwoFkxYECUhpRSlGgVTegDaBZHQJAaDw7T2Fp1fZQoaAZoCWgPQwifk943vkJmQJSGlFKUaBVN6ANoFkdAkCA7Qswta3V9lChoBmgJaA9DCK4s0Vnmk2ZAlIaUUpRoFU3oA2gWR0CQIpt/nW8RdX2UKGgGaAloD0MIATJ07CCOZECUhpRSlGgVTegDaBZHQJAl+89Oh011fZQoaAZoCWgPQwgt6pPc4bxjQJSGlFKUaBVN6ANoFkdAkCYYH9m6G3V9lChoBmgJaA9DCCdPWU1XQmFAlIaUUpRoFU3oA2gWR0CQJ5u14Pf9dX2UKGgGaAloD0MI9DY2O9JzYUCUhpRSlGgVTegDaBZHQJAzOM5wOvt1fZQoaAZoCWgPQwhBgAwdO3pjQJSGlFKUaBVN6ANoFkdAkEvDKcNH6XV9lChoBmgJaA9DCI7O+SmO03FAlIaUUpRoFU3KA2gWR0CQTSCpm29ddX2UKGgGaAloD0MIoZ3TLFDNZECUhpRSlGgVTegDaBZHQJBS5wZOzpp1fZQoaAZoCWgPQwi7Cik/KWBhQJSGlFKUaBVN6ANoFkdAkFWvMW43FXV9lChoBmgJaA9DCH0+yoiLO2NAlIaUUpRoFU3oA2gWR0CQVrnaWX1KdX2UKGgGaAloD0MIW9O845R7ZECUhpRSlGgVTegDaBZHQJBbZsQ/X5F1fZQoaAZoCWgPQwjsavKU1dBgQJSGlFKUaBVN6ANoFkdAkFwIfW+XaHV9lChoBmgJaA9DCAzohTsXXWhAlIaUUpRoFU3oA2gWR0CQX6sWfseGdX2UKGgGaAloD0MIhbAaS1hWaECUhpRSlGgVTegDaBZHQJBf1GQSzxB1fZQoaAZoCWgPQwgBwocSrXhmQJSGlFKUaBVN6ANoFkdAkGH59ZzPr3V9lChoBmgJaA9DCLKbGf1ov2BAlIaUUpRoFU3oA2gWR0CQZ/vovBacdX2UKGgGaAloD0MI/BnerEFYZUCUhpRSlGgVTegDaBZHQJBqTutwJgN1fZQoaAZoCWgPQwjkFYieFGZnQJSGlFKUaBVN6ANoFkdAkG2ShJyyU3V9lChoBmgJaA9DCCMw1jew7WRAlIaUUpRoFU3oA2gWR0CQba9IwudxdX2UKGgGaAloD0MImBQfnxBUZECUhpRSlGgVTegDaBZHQJBvN9Vmz0J1fZQoaAZoCWgPQwg/rDdqhYNlQJSGlFKUaBVN6ANoFkdAkHrIacZtN3V9lChoBmgJaA9DCDp4JjTJFGRAlIaUUpRoFU3oA2gWR0CQlB71ZkkKdX2UKGgGaAloD0MIorQ3+EKXYkCUhpRSlGgVTegDaBZHQJCVmkrPMSt1fZQoaAZoCWgPQwjaAdcVM5xKQJSGlFKUaBVLxGgWR0CQme+VTrE+dX2UKGgGaAloD0MItU5cjtc0YkCUhpRSlGgVTegDaBZHQJCbMpRXOnl1fZQoaAZoCWgPQwgc8PlhBJVmQJSGlFKUaBVN6ANoFkdAkJ5IeHSF5HV9lChoBmgJaA9DCGeeXFOgoWBAlIaUUpRoFU3oA2gWR0CQn3HYYixFdX2UKGgGaAloD0MIlUVhF8UoYkCUhpRSlGgVTegDaBZHQJCk1Ge+VTt1fZQoaAZoCWgPQwh4tdyZCTNmQJSGlFKUaBVN6ANoFkdAkKWMdHUc43V9lChoBmgJaA9DCEaYolwaYmZAlIaUUpRoFU3oA2gWR0CQqVCgbp/xdX2UKGgGaAloD0MIFy1A22oAaUCUhpRSlGgVTegDaBZHQJCpegHu7Yl1fZQoaAZoCWgPQwgc0NIV7HtgQJSGlFKUaBVN6ANoFkdAkKuxMFlkH3V9lChoBmgJaA9DCFkzMshdkWZAlIaUUpRoFU3oA2gWR0CQsc31zySWdX2UKGgGaAloD0MIJZF9kOW5ZECUhpRSlGgVTegDaBZHQJC0Nx0dRzl1fZQoaAZoCWgPQwhXmL7XkNVxQJSGlFKUaBVNywNoFkdAkLXvbj94vHV9lChoBmgJaA9DCIdT5uYbP2VAlIaUUpRoFU3oA2gWR0CQt5TPjXFtdX2UKGgGaAloD0MI/Io1XCRBcUCUhpRSlGgVTdEBaBZHQJC350ZFXq91fZQoaAZoCWgPQwieew+XHBdkQJSGlFKUaBVN6ANoFkdAkLkL961LJ3V9lChoBmgJaA9DCB1znrEv02JAlIaUUpRoFU3oA2gWR0CQ3dUKRdQgdX2UKGgGaAloD0MIcvvlk5X6Y0CUhpRSlGgVTegDaBZHQJDfakXUH6d1fZQoaAZoCWgPQwiq9BPOboBjQJSGlFKUaBVN6ANoFkdAkORIEnssx3V9lChoBmgJaA9DCJet9UVCn2ZAlIaUUpRoFU3oA2gWR0CQ5ZygPEsKdX2UKGgGaAloD0MILIL/rWRWZECUhpRSlGgVTegDaBZHQJDosyzolld1fZQoaAZoCWgPQwh7Lei9sTJgQJSGlFKUaBVN6ANoFkdAkO76MvRJE3V9lChoBmgJaA9DCBEBh1ClwmVAlIaUUpRoFU3oA2gWR0CQ76uVHFxXdX2UKGgGaAloD0MIcVrwoq99Y0CUhpRSlGgVTegDaBZHQJDzW/j81oB1fZQoaAZoCWgPQwiN0M/U6xliQJSGlFKUaBVN6ANoFkdAkPOC2x6fJ3V9lChoBmgJaA9DCJDdBUqK1GRAlIaUUpRoFU3oA2gWR0CQ9bH7xd6cdX2UKGgGaAloD0MIZoUi3U+pZUCUhpRSlGgVTegDaBZHQJD7XHcUM5R1fZQoaAZoCWgPQwjWARB3dYZhQJSGlFKUaBVN6ANoFkdAkP2afe1rqXV9lChoBmgJaA9DCKDejJoveWdAlIaUUpRoFU3oA2gWR0CQ/0GSIP9UdX2UKGgGaAloD0MIiSXl7vMfZUCUhpRSlGgVTegDaBZHQJEA1T5wfhd1fZQoaAZoCWgPQwipZ0Eo7w1mQJSGlFKUaBVN6ANoFkdAkQEdnCfpU3V9lChoBmgJaA9DCOc1donqUGJAlIaUUpRoFU3oA2gWR0CRAjy5I6KcdX2UKGgGaAloD0MI9dbAVgk2Y0CUhpRSlGgVTegDaBZHQJESpSXMQmN1fZQoaAZoCWgPQwg4u7VMBgxhQJSGlFKUaBVN6ANoFkdAkSeFvybx3HV9lChoBmgJaA9DCA1v1uB9TGZAlIaUUpRoFU3oA2gWR0CRLamjj7yhdX2UKGgGaAloD0MIPgeWI2TwYECUhpRSlGgVTegDaBZHQJEvVsYVIqd1fZQoaAZoCWgPQwgl6gWfZq1hQJSGlFKUaBVN6ANoFkdAkTNY9X9zfnV9lChoBmgJaA9DCDtxOV6B0WFAlIaUUpRoFU3oA2gWR0CROvtHxz7udX2UKGgGaAloD0MIBi6PNaNFZECUhpRSlGgVTegDaBZHQJE7qJxeb/h1fZQoaAZoCWgPQwgnF2NgHX9lQJSGlFKUaBVN6ANoFkdAkT9y619fC3V9lChoBmgJaA9DCC/gZYYNimdAlIaUUpRoFU3oA2gWR0CRP5vHcUM5dX2UKGgGaAloD0MITWa8rXSaZ0CUhpRSlGgVTegDaBZHQJFBz8CPp6h1fZQoaAZoCWgPQwgGY0Si0KFhQJSGlFKUaBVN6ANoFkdAkUe6dpZfUnV9lChoBmgJaA9DCNU9srlqX2dAlIaUUpRoFU3oA2gWR0CRSfGCqZMMdX2UKGgGaAloD0MIhLpIoSzXaECUhpRSlGgVTegDaBZHQJFLlA/s3Q51fZQoaAZoCWgPQwgY7lwYaRhhQJSGlFKUaBVN6ANoFkdAkU0euq3mWHV9lChoBmgJaA9DCCo5J/ZQ82RAlIaUUpRoFU3oA2gWR0CRTWbpNbkfdX2UKGgGaAloD0MImL1sO+0IaECUhpRSlGgVTegDaBZHQJFOe/j81oB1fZQoaAZoCWgPQwguOllqvUZhQJSGlFKUaBVN6ANoFkdAkV9qWHDaXnV9lChoBmgJaA9DCHQkl/8Q4WdAlIaUUpRoFU3oA2gWR0CRYO0163RYdWUu"
|
74 |
},
|
75 |
"ep_success_buffer": {
|
76 |
":type:": "<class 'collections.deque'>",
|
77 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
78 |
},
|
79 |
+
"_n_updates": 248,
|
80 |
"n_steps": 1024,
|
81 |
"gamma": 0.999,
|
82 |
"gae_lambda": 0.98,
|
ppo_lunarlander/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 sha256:1981be90393810965eea7142eddb9d413a5215447605b3160e21ef59e0f53a53
|
3 |
size 87929
|
ppo_lunarlander/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43393
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4311b34f8a9fe420003fe2e951485ae9a60d628e18e950fbe219f19bc6e75258
|
3 |
size 43393
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 271.7438612640243, "std_reward": 14.746747570335996, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-16T09:41:09.255495"}
|