init LL-v2
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +21 -21
- 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: 278.73 +/- 12.88
|
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 0x7fde949088b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fde94908940>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fde949089d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fde94908a60>", "_build": "<function ActorCriticPolicy._build at 0x7fde94908af0>", "forward": "<function ActorCriticPolicy.forward at 0x7fde94908b80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fde94908c10>", "_predict": "<function ActorCriticPolicy._predict at 0x7fde94908ca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fde94908d30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fde94908dc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fde94908e50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fde948fcf90>"}, "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": 1670347093052903014, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "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 0x7f246401e550>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f246401e5e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f246401e670>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f246401e700>", "_build": "<function ActorCriticPolicy._build at 0x7f246401e790>", "forward": "<function ActorCriticPolicy.forward at 0x7f246401e820>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f246401e8b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f246401e940>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f246401e9d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f246401ea60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f246401eaf0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f2464017bd0>"}, "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": 1670427035845804392, "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": 984, "n_steps": 1024, "gamma": 0.9999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 8, "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": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.12.1+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d7bcb075c3180e4fd22f92d59a5a14f769f8ab86e5ebda4ec640bb79f8ac754
|
3 |
+
size 147075
|
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'>",
|
@@ -66,24 +66,24 @@
|
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
-
"_current_progress_remaining": -0.
|
70 |
"ep_info_buffer": {
|
71 |
":type:": "<class 'collections.deque'>",
|
72 |
-
":serialized:": "
|
73 |
},
|
74 |
"ep_success_buffer": {
|
75 |
":type:": "<class 'collections.deque'>",
|
76 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
"n_steps": 1024,
|
80 |
-
"gamma": 0.
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
"batch_size": 64,
|
86 |
-
"n_epochs":
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "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"
|
|
|
4 |
":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
"__module__": "stable_baselines3.common.policies",
|
6 |
"__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7f246401e550>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f246401e5e0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f246401e670>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f246401e700>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f246401e790>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f246401e820>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f246401e8b0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f246401e940>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f246401e9d0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f246401ea60>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f246401eaf0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f2464017bd0>"
|
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": 1670427035845804392,
|
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": 984,
|
79 |
"n_steps": 1024,
|
80 |
+
"gamma": 0.9999,
|
81 |
"gae_lambda": 0.98,
|
82 |
"ent_coef": 0.01,
|
83 |
"vf_coef": 0.5,
|
84 |
"max_grad_norm": 0.5,
|
85 |
"batch_size": 64,
|
86 |
+
"n_epochs": 8,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
":serialized:": "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"
|
ppo-LunarLander-v2/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87865
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48490ad9d5d85eaa5228d36c0820439de552104a4cd0fbdf28f024adbd0ab55a
|
3 |
size 87865
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43201
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bae21b452484c6779e4c55e392a1aa4d9693513fd9c02f5ead43a94e68210b48
|
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": 278.7251517404432, "std_reward": 12.882263996109339, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-07T16:10:30.801820"}
|