unit 1, new code from google colab
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +24 -24
- ppo-LunarLander-v2/policy.optimizer.pth +2 -2
- ppo-LunarLander-v2/policy.pth +2 -2
- ppo-LunarLander-v2/system_info.txt +5 -5
- 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: 132.64 +/- 104.73
|
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 0x1592afca0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1592afd30>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1592afdc0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1592afe50>", "_build": "<function ActorCriticPolicy._build at 0x1592afee0>", "forward": "<function ActorCriticPolicy.forward at 0x1592aff70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1592b3040>", "_predict": "<function ActorCriticPolicy._predict at 0x1592b30d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1592b3160>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x1592b31f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x1592b3280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x1592b1f00>"}, "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:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1507328, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1669321651583449596, "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": -0.004885333333333408, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 496, "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": "macOS-12.6-arm64-arm-64bit Darwin Kernel Version 21.6.0: Mon Aug 22 20:19:52 PDT 2022; root:xnu-8020.140.49~2/RELEASE_ARM64_T6000", "Python": "3.9.13", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0", "GPU Enabled": "False", "Numpy": "1.23.5", "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 0x7fb26fab75e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb26fab7670>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb26fab7700>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb26fab7790>", "_build": "<function ActorCriticPolicy._build at 0x7fb26fab7820>", "forward": "<function ActorCriticPolicy.forward at 0x7fb26fab78b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb26fab7940>", "_predict": "<function ActorCriticPolicy._predict at 0x7fb26fab79d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb26fab7a60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb26fab7af0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb26fab7b80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fb26faaee10>"}, "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": 500736, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1670444502940374729, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKafzb0kuiI/Gh8zPVYvZr5yo7A8v7W2vAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0014719999999999178, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1956, "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:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "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": "3.8.15", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0+cu116", "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 sha256:0c40280d0960620617a58d174e631787c010217568ca2fee82bc9b45ebe3c496
|
3 |
+
size 146549
|
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
|
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": "<
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
@@ -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":
|
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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
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:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+
|
90 |
},
|
91 |
"clip_range_vf": null,
|
92 |
"normalize_advantage": true,
|
|
|
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 0x7fb26fab75e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb26fab7670>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb26fab7700>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb26fab7790>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fb26fab7820>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fb26fab78b0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb26fab7940>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fb26fab79d0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb26fab7a60>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb26fab7af0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb26fab7b80>",
|
18 |
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7fb26faaee10>"
|
20 |
},
|
21 |
"verbose": 1,
|
22 |
"policy_kwargs": {},
|
|
|
35 |
},
|
36 |
"action_space": {
|
37 |
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
"n": 4,
|
40 |
"_shape": [],
|
41 |
"dtype": "int64",
|
42 |
"_np_random": null
|
43 |
},
|
44 |
+
"n_envs": 1,
|
45 |
+
"num_timesteps": 500736,
|
46 |
+
"_total_timesteps": 500000,
|
47 |
"_num_timesteps_at_start": 0,
|
48 |
"seed": null,
|
49 |
"action_noise": null,
|
50 |
+
"start_time": 1670444502940374729,
|
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:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKafzb0kuiI/Gh8zPVYvZr5yo7A8v7W2vAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
60 |
},
|
61 |
"_last_episode_starts": {
|
62 |
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
64 |
},
|
65 |
"_last_original_obs": null,
|
66 |
"_episode_num": 0,
|
67 |
"use_sde": false,
|
68 |
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.0014719999999999178,
|
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": 1956,
|
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 sha256:985470793b735b340a331dcf7fa8145c815716d4bd0699fecb4cdbe6042de131
|
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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35a922d284ba819745e422942e6a7eb017428d3ce357b8b0fa70571f200aca1f
|
3 |
+
size 43201
|
ppo-LunarLander-v2/system_info.txt
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
OS:
|
2 |
-
Python: 3.
|
3 |
Stable-Baselines3: 1.6.2
|
4 |
-
PyTorch: 1.13.0
|
5 |
-
GPU Enabled:
|
6 |
-
Numpy: 1.
|
7 |
Gym: 0.21.0
|
|
|
1 |
+
OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
|
2 |
+
Python: 3.8.15
|
3 |
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.0+cu116
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
Gym: 0.21.0
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 132.63964996846647, "std_reward": 104.72719290382321, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-07T20:48:34.633364"}
|