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 +26 -26
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
README.md
CHANGED
@@ -10,7 +10,7 @@ model-index:
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
-
value:
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
|
|
10 |
results:
|
11 |
- metrics:
|
12 |
- type: mean_reward
|
13 |
+
value: 296.66 +/- 19.59
|
14 |
name: mean_reward
|
15 |
task:
|
16 |
type: reinforcement-learning
|
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 0x7f8ee5ee13b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f8ee5ee1440>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f8ee5ee14d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f8ee5ee1560>", "_build": "<function ActorCriticPolicy._build at 0x7f8ee5ee15f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f8ee5ee1680>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f8ee5ee1710>", "_predict": "<function ActorCriticPolicy._predict at 0x7f8ee5ee17a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f8ee5ee1830>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f8ee5ee18c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f8ee5ee1950>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f8ee5f2b870>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652962079.5083396, "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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f176965eb00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f176965eb90>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f176965ec20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f176965ecb0>", "_build": "<function ActorCriticPolicy._build at 0x7f176965ed40>", "forward": "<function ActorCriticPolicy.forward at 0x7f176965edd0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f176965ee60>", "_predict": "<function ActorCriticPolicy._predict at 0x7f176965eef0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f176965ef80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1769662050>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f17696620e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f17696af600>"}, "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 5013504, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1653210897.3851593, "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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0027007999999999477, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1224, "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-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+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 sha256:5b60a3ef49ecad7402d906d784a04931d6a7bf2c854b59044d82664126a742c7
|
3 |
+
size 144092
|
ppo-LunarLander-v2/data
CHANGED
@@ -1,28 +1,28 @@
|
|
1 |
{
|
2 |
"policy_class": {
|
3 |
":type:": "<class 'abc.ABCMeta'>",
|
4 |
-
":serialized:": "
|
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": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
-
":serialized:": "
|
26 |
"dtype": "float32",
|
27 |
"_shape": [
|
28 |
8
|
@@ -35,47 +35,47 @@
|
|
35 |
},
|
36 |
"action_space": {
|
37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
-
":serialized:": "
|
39 |
"n": 4,
|
40 |
"_shape": [],
|
41 |
"dtype": "int64",
|
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": {
|
54 |
":type:": "<class 'function'>",
|
55 |
-
":serialized:": "
|
56 |
},
|
57 |
"_last_obs": {
|
58 |
":type:": "<class 'numpy.ndarray'>",
|
59 |
-
":serialized:": "
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
-
":serialized:": "
|
64 |
},
|
65 |
"_last_original_obs": null,
|
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:": "
|
77 |
},
|
78 |
-
"_n_updates":
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
@@ -86,7 +86,7 @@
|
|
86 |
"n_epochs": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
-
":serialized:": "
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
|
|
1 |
{
|
2 |
"policy_class": {
|
3 |
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f176965eb00>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f176965eb90>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f176965ec20>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f176965ecb0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f176965ed40>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f176965edd0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f176965ee60>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f176965eef0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f176965ef80>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1769662050>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f17696620e0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f17696af600>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
23 |
"observation_space": {
|
24 |
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
"dtype": "float32",
|
27 |
"_shape": [
|
28 |
8
|
|
|
35 |
},
|
36 |
"action_space": {
|
37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
"n": 4,
|
40 |
"_shape": [],
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 5013504,
|
46 |
+
"_total_timesteps": 5000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1653210897.3851593,
|
51 |
"learning_rate": 0.0003,
|
52 |
"tensorboard_log": null,
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
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'>",
|
63 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.0027007999999999477,
|
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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
},
|
78 |
+
"_n_updates": 1224,
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
|
|
86 |
"n_epochs": 4,
|
87 |
"clip_range": {
|
88 |
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffcc0f650b67990ba129b43b2c6a842489d714a1d23944e59945414ff376af6e
|
3 |
+
size 84893
|
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 sha256:9ef46cae866c85ec229bc755deea58d3caa0873543ed5d30f98137d307cc6b32
|
3 |
size 43201
|
replay.mp4
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 sha256:3dd2f4b0af27f4877253db5fd7810133a782917645e77ab78394fb38e160bdfe
|
3 |
+
size 174558
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 296.6569883643866, "std_reward": 19.586377424015033, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-22T10:16:57.931493"}
|