SamTheCoder777 commited on
Commit
e8ff4bc
1 Parent(s): f1a5b5d

Upload PPO LunarLander-v2 trained agent

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
- value: -300.78 +/- 110.05
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: LunarLander-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: 281.77 +/- 20.03
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 0x7ff8260dbe20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff8260dbeb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff8260dbf40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff8260e0040>", "_build": "<function ActorCriticPolicy._build at 0x7ff8260e00d0>", "forward": "<function ActorCriticPolicy.forward at 0x7ff8260e0160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff8260e01f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff8260e0280>", "_predict": "<function ActorCriticPolicy._predict at 0x7ff8260e0310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff8260e03a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff8260e0430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff8260e04c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff8260d2d80>"}, "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": 1, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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-5.15.90.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Jan 27 02:56:13 UTC 2023", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "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 0x7f7f784f0b80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7f784f0c10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7f784f0ca0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7f784f0d30>", "_build": "<function ActorCriticPolicy._build at 0x7f7f784f0dc0>", "forward": "<function ActorCriticPolicy.forward at 0x7f7f784f0e50>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f7f784f0ee0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7f784f0f70>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7f784f1000>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7f784f1090>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7f784f1120>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7f784f11b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f7f784eb280>"}, "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": 1, "num_timesteps": 5625856, "_total_timesteps": 50000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1678139263849327944, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAANrOhz1kRLo/mgibPoG4DL6RHlM+cqq2PgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.88748288, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 21972, "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-5.15.90.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Jan 27 02:56:13 UTC 2023", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu117", "GPU Enabled": "True", "Numpy": "1.24.2", "Gym": "0.21.0"}}
ppo-LunarLander-v2.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d0bf2efe531761172d2db61bc7d2b19636cc0e8398290c05c1c7b48b4a9f80d
3
- size 53193
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecf0f1292272d64490ae686b40701d315fc4cfedd7170ee50b6b5810141b641a
3
+ size 146764
ppo-LunarLander-v2/data CHANGED
@@ -4,20 +4,20 @@
4
  ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
5
  "__module__": "stable_baselines3.common.policies",
6
  "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ",
7
- "__init__": "<function ActorCriticPolicy.__init__ at 0x7ff8260dbe20>",
8
- "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff8260dbeb0>",
9
- "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff8260dbf40>",
10
- "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff8260e0040>",
11
- "_build": "<function ActorCriticPolicy._build at 0x7ff8260e00d0>",
12
- "forward": "<function ActorCriticPolicy.forward at 0x7ff8260e0160>",
13
- "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff8260e01f0>",
14
- "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff8260e0280>",
15
- "_predict": "<function ActorCriticPolicy._predict at 0x7ff8260e0310>",
16
- "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff8260e03a0>",
17
- "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff8260e0430>",
18
- "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff8260e04c0>",
19
  "__abstractmethods__": "frozenset()",
20
- "_abc_impl": "<_abc._abc_data object at 0x7ff8260d2d80>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
@@ -43,28 +43,40 @@
43
  "_np_random": null
44
  },
45
  "n_envs": 1,
46
- "num_timesteps": 0,
47
- "_total_timesteps": 0,
48
  "_num_timesteps_at_start": 0,
49
  "seed": null,
50
  "action_noise": null,
51
- "start_time": null,
52
  "learning_rate": 0.0003,
53
  "tensorboard_log": null,
54
  "lr_schedule": {
55
  ":type:": "<class 'function'>",
56
  ":serialized:": "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"
57
  },
58
- "_last_obs": null,
59
- "_last_episode_starts": null,
 
 
 
 
 
 
60
  "_last_original_obs": null,
61
  "_episode_num": 0,
62
  "use_sde": false,
63
  "sde_sample_freq": -1,
64
- "_current_progress_remaining": 1,
65
- "ep_info_buffer": null,
66
- "ep_success_buffer": null,
67
- "_n_updates": 0,
 
 
 
 
 
 
68
  "n_steps": 1024,
69
  "gamma": 0.999,
70
  "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 0x7f7f784f0b80>",
8
+ "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7f784f0c10>",
9
+ "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7f784f0ca0>",
10
+ "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f7f784f0d30>",
11
+ "_build": "<function ActorCriticPolicy._build at 0x7f7f784f0dc0>",
12
+ "forward": "<function ActorCriticPolicy.forward at 0x7f7f784f0e50>",
13
+ "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f7f784f0ee0>",
14
+ "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7f784f0f70>",
15
+ "_predict": "<function ActorCriticPolicy._predict at 0x7f7f784f1000>",
16
+ "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f7f784f1090>",
17
+ "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7f784f1120>",
18
+ "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f7f784f11b0>",
19
  "__abstractmethods__": "frozenset()",
20
+ "_abc_impl": "<_abc._abc_data object at 0x7f7f784eb280>"
21
  },
22
  "verbose": 1,
23
  "policy_kwargs": {},
 
43
  "_np_random": null
44
  },
45
  "n_envs": 1,
46
+ "num_timesteps": 5625856,
47
+ "_total_timesteps": 50000000,
48
  "_num_timesteps_at_start": 0,
49
  "seed": null,
50
  "action_noise": null,
51
+ "start_time": 1678139263849327944,
52
  "learning_rate": 0.0003,
53
  "tensorboard_log": null,
54
  "lr_schedule": {
55
  ":type:": "<class 'function'>",
56
  ":serialized:": "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"
57
  },
58
+ "_last_obs": {
59
+ ":type:": "<class 'numpy.ndarray'>",
60
+ ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAANrOhz1kRLo/mgibPoG4DL6RHlM+cqq2PgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
61
+ },
62
+ "_last_episode_starts": {
63
+ ":type:": "<class 'numpy.ndarray'>",
64
+ ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
65
+ },
66
  "_last_original_obs": null,
67
  "_episode_num": 0,
68
  "use_sde": false,
69
  "sde_sample_freq": -1,
70
+ "_current_progress_remaining": 0.88748288,
71
+ "ep_info_buffer": {
72
+ ":type:": "<class 'collections.deque'>",
73
+ ":serialized:": "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"
74
+ },
75
+ "ep_success_buffer": {
76
+ ":type:": "<class 'collections.deque'>",
77
+ ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
78
+ },
79
+ "_n_updates": 21972,
80
  "n_steps": 1024,
81
  "gamma": 0.999,
82
  "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 sha256:2497affac19a461e040f7a57c9a5933e93b10b5579b0a3d91d7d3978070520ec
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8640d7a4d9816ebfae1e679dc608746bc9b57580f31b81bddf60121d8233735e
3
+ size 87929
ppo-LunarLander-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bf051fb733d59a84fbf59ef94c17f1a5b6aafa7d7bc10cef7929e6e8ab1b77a
3
  size 43393
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:389dc3ee4290984335b467963104aaa05f4bdbf2ceed7311234fd7bae4c7753d
3
  size 43393
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -300.78371632881465, "std_reward": 110.04854551147912, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-06T15:45:31.677307"}
 
1
+ {"mean_reward": 281.7652902656754, "std_reward": 20.033403517810488, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-06T18:53:05.419113"}