Commit
•
05e4b77
1
Parent(s):
367e38f
Double training timesteps to 1 mil
Browse files- README.md +1 -1
- config.json +1 -1
- lunarLander.zip +2 -2
- lunarLander/data +18 -18
- lunarLander/policy.optimizer.pth +1 -1
- lunarLander/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: 235.21 +/- 18.51
|
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 0x7fb007d16790>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb007d16820>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb007d168b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb007d16940>", "_build": "<function ActorCriticPolicy._build at 0x7fb007d169d0>", "forward": "<function ActorCriticPolicy.forward at 0x7fb007d16a60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb007d16af0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb007d16b80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb007d16c10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb007d16ca0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb007d16d30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fb007d14300>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 1671386346433811250, "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-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "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 0x7f3aa80e7430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3aa80e74c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3aa80e7550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3aa80e75e0>", "_build": "<function ActorCriticPolicy._build at 0x7f3aa80e7670>", "forward": "<function ActorCriticPolicy.forward at 0x7f3aa80e7700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3aa80e7790>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3aa80e7820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3aa80e78b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3aa80e7940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3aa80e79d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f3aa80e8090>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "gAWVnwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAAAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/5RoCksIhZSMAUOUdJRSlIwEaGlnaJRoEiiWIAAAAAAAAAAAAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAf5RoCksIhZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolggAAAAAAAAAAAAAAAAAAACUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYIAAAAAAAAAAAAAAAAAAAAlGghSwiFlGgVdJRSlIwKX25wX3JhbmRvbZROdWIu", "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": 1671393311743840399, "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": "3.8.16", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
lunarLander.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:d143fb0deec99465f2e734755582c85f31eeed2625b7b1671f08a920c6855eaf
|
3 |
+
size 147218
|
lunarLander/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 0x7f3aa80e7430>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3aa80e74c0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3aa80e7550>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3aa80e75e0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f3aa80e7670>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f3aa80e7700>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3aa80e7790>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f3aa80e7820>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3aa80e78b0>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3aa80e7940>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3aa80e79d0>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f3aa80e8090>"
|
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": 1671393311743840399,
|
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,
|
lunarLander/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28ca704a37fc11f21b86ba55f45d838ddcc4a380ad85b1baafcd263f09257c31
|
3 |
size 87929
|
lunarLander/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 sha256:40b72015c529bc52e9246493979e199d9be194cb81cbcfc1297269d13796249c
|
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": 235.21079523193816, "std_reward": 18.50632646458401, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-18T20:15:08.150582"}
|