First model
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2-test.zip +2 -2
- ppo-LunarLander-v2-test/data +18 -18
- ppo-LunarLander-v2-test/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2-test/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: 243.15 +/- 18.87
|
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 0x7f809d2e73b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f809d2e7440>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f809d2e74d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f809d2e7560>", "_build": "<function ActorCriticPolicy._build at 0x7f809d2e75f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f809d2e7680>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f809d2e7710>", "_predict": "<function ActorCriticPolicy._predict at 0x7f809d2e77a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f809d2e7830>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f809d2e78c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f809d2e7950>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f809d32e7b0>"}, "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": 1652646620.0994034, "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": 124, "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:": "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 0x7f696e518170>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f696e518200>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f696e518290>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f696e518320>", "_build": "<function ActorCriticPolicy._build at 0x7f696e5183b0>", "forward": "<function ActorCriticPolicy.forward at 0x7f696e518440>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f696e5184d0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f696e518560>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f696e5185f0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f696e518680>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f696e518710>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f696e555c60>"}, "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": 1652808262.577061, "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"}}
|
ppo-LunarLander-v2-test.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 sha256:7be84d77ad01774a026518f622a8b49ebac11d5fd7801049267e87d13d360365
|
3 |
+
size 144049
|
ppo-LunarLander-v2-test/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'>",
|
@@ -69,13 +69,13 @@
|
|
69 |
"_current_progress_remaining": -0.015808000000000044,
|
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": 0.999,
|
81 |
"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 0x7f696e518170>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f696e518200>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f696e518290>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f696e518320>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f696e5183b0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f696e518440>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f696e5184d0>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f696e518560>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f696e5185f0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f696e518680>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f696e518710>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f696e555c60>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
42 |
"_np_random": null
|
43 |
},
|
44 |
"n_envs": 16,
|
45 |
+
"num_timesteps": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1652808262.577061,
|
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'>",
|
|
|
69 |
"_current_progress_remaining": -0.015808000000000044,
|
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": 248,
|
79 |
"n_steps": 1024,
|
80 |
"gamma": 0.999,
|
81 |
"gae_lambda": 0.98,
|
ppo-LunarLander-v2-test/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84829
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c11abdc1d92a04bb81a80b4881f04ba90a4557223ed4b2348df9968b1baf186c
|
3 |
size 84829
|
ppo-LunarLander-v2-test/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 sha256:26821f5c24900eb41a63b786b8a1f7287f40481c0dd4078391659e120ff38770
|
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 sha256:1399d890ac0788e8b50f0adee78e0d4b3f0228eeea62bb0fdcd475b68bcb7332
|
3 |
+
size 239145
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 243.1544488645498, "std_reward": 18.866137554015424, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-17T17:45:06.060501"}
|