meln1k commited on
Commit
d201b00
1 Parent(s): 64ffb90
README.md CHANGED
@@ -10,7 +10,7 @@ model-index:
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
- value: 267.37 +/- 23.07
14
  name: mean_reward
15
  task:
16
  type: reinforcement-learning
 
10
  results:
11
  - metrics:
12
  - type: mean_reward
13
+ value: 285.92 +/- 20.13
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 0x7f214ebadca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f214ebadd30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f214ebaddc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f214ebade50>", "_build": "<function ActorCriticPolicy._build at 0x7f214ebadee0>", "forward": "<function ActorCriticPolicy.forward at 0x7f214ebadf70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f214ebb2040>", "_predict": "<function ActorCriticPolicy._predict at 0x7f214ebb20d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f214ebb2160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f214ebb21f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f214ebb2280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f214ebae500>"}, "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": 2506752, "_total_timesteps": 2500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652125678.1445148, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_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": -0.0027007999999999477, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 612, "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-5.11.0-38-generic-x86_64-with-glibc2.31 #42~20.04.1-Ubuntu SMP Tue Sep 28 20:41:07 UTC 2021", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "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 0x7f9026771ca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9026771d30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9026771dc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9026771e50>", "_build": "<function ActorCriticPolicy._build at 0x7f9026771ee0>", "forward": "<function ActorCriticPolicy.forward at 0x7f9026771f70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9026775040>", "_predict": "<function ActorCriticPolicy._predict at 0x7f90267750d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9026775160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f90267751f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9026775280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f90268eed00>"}, "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": 10010624, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1652133598.2034173, "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": -0.0010623999999999079, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 2444, "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-5.11.0-38-generic-x86_64-with-glibc2.31 #42~20.04.1-Ubuntu SMP Tue Sep 28 20:41:07 UTC 2021", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}
ppo-LunarLander-v2.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c9943cacd4b73948cf269da877d984e67e5ecf3031d18a7816064d146f7bcbf
3
- size 143252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb76d805697923c18abe016882e2d3e77f485b51c6cefab4b436ba73a11c2cda
3
+ size 144158
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 0x7f214ebadca0>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f214ebadd30>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f214ebaddc0>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f214ebade50>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7f214ebadee0>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7f214ebadf70>",
13
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f214ebb2040>",
14
- "_predict": "<function ActorCriticPolicy._predict at 0x7f214ebb20d0>",
15
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f214ebb2160>",
16
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f214ebb21f0>",
17
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f214ebb2280>",
18
  "__abstractmethods__": "frozenset()",
19
- "_abc_impl": "<_abc._abc_data object at 0x7f214ebae500>"
20
  },
21
  "verbose": 1,
22
  "policy_kwargs": {},
@@ -42,19 +42,22 @@
42
  "_np_random": null
43
  },
44
  "n_envs": 16,
45
- "num_timesteps": 2506752,
46
- "_total_timesteps": 2500000,
47
  "_num_timesteps_at_start": 0,
48
  "seed": null,
49
  "action_noise": null,
50
- "start_time": 1652125678.1445148,
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": null,
 
 
 
58
  "_last_episode_starts": {
59
  ":type:": "<class 'numpy.ndarray'>",
60
  ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
@@ -63,16 +66,16 @@
63
  "_episode_num": 0,
64
  "use_sde": false,
65
  "sde_sample_freq": -1,
66
- "_current_progress_remaining": -0.0027007999999999477,
67
  "ep_info_buffer": {
68
  ":type:": "<class 'collections.deque'>",
69
- ":serialized:": "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"
70
  },
71
  "ep_success_buffer": {
72
  ":type:": "<class 'collections.deque'>",
73
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
74
  },
75
- "_n_updates": 612,
76
  "n_steps": 1024,
77
  "gamma": 0.999,
78
  "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 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 0x7f9026771ca0>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9026771d30>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9026771dc0>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9026771e50>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f9026771ee0>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f9026771f70>",
13
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9026775040>",
14
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f90267750d0>",
15
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9026775160>",
16
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f90267751f0>",
17
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9026775280>",
18
  "__abstractmethods__": "frozenset()",
19
+ "_abc_impl": "<_abc._abc_data object at 0x7f90268eed00>"
20
  },
21
  "verbose": 1,
22
  "policy_kwargs": {},
 
42
  "_np_random": null
43
  },
44
  "n_envs": 16,
45
+ "num_timesteps": 10010624,
46
+ "_total_timesteps": 10000000,
47
  "_num_timesteps_at_start": 0,
48
  "seed": null,
49
  "action_noise": null,
50
+ "start_time": 1652133598.2034173,
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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
 
66
  "_episode_num": 0,
67
  "use_sde": false,
68
  "sde_sample_freq": -1,
69
+ "_current_progress_remaining": -0.0010623999999999079,
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": 2444,
79
  "n_steps": 1024,
80
  "gamma": 0.999,
81
  "gae_lambda": 0.98,
ppo-LunarLander-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:351465e51b46e95aa34cdd1c0cd8d37eac2f66dc610d0bc5609fd7710377244a
3
  size 84893
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d4e9ed0314503a6c175f2ab2c6a79e2a2e2c3f64871b0f70ab758067a7ec9b
3
  size 84893
ppo-LunarLander-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e5892ce18c7e2a6df07f390a5b0bb490210d9a792556f1224e4cc43503b736a
3
  size 43201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97af58d8eec413ab1bc4d8bef208b91ca8ece89244d80897cc5f7b6ad075a76a
3
  size 43201
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4576ff97fcc0c1a93c7e21bf3d33907b4481135cd27aacb1b30d7110365cd5b8
3
- size 191055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31924627e8cf7e02b1f0453a0c3894fe6a9ccc81730dc5954b40033eda8acf24
3
+ size 187189
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 267.36909513337594, "std_reward": 23.067034458833696, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-09T22:20:29.303998"}
 
1
+ {"mean_reward": 285.9203131038186, "std_reward": 20.128335678563207, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T01:24:32.110316"}