Commit
•
30241e2
1
Parent(s):
d7533bf
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- ppo-LunarLander-v2.zip +2 -2
- ppo-LunarLander-v2/data +22 -22
- ppo-LunarLander-v2/policy.optimizer.pth +1 -1
- ppo-LunarLander-v2/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: 213.40 +/- 79.12
|
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 0x7f2d0ba06170>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f2d0ba06200>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f2d0ba06290>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f2d0ba06320>", "_build": "<function ActorCriticPolicy._build at 0x7f2d0ba063b0>", "forward": "<function ActorCriticPolicy.forward at 0x7f2d0ba06440>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f2d0ba064d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f2d0ba06560>", "_predict": "<function ActorCriticPolicy._predict at 0x7f2d0ba065f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f2d0ba06680>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f2d0ba06710>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f2d0ba067a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f2d0b9b7c80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 100352, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718987887553194843, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAACbOgD0b+Uw/wgHZvnyed74yVhu9zwWevgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0035199999999999676, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 476, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": "Generator(PCG64)"}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
|
|
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 0x7b90846ec4c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b90846ec550>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b90846ec5e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b90846ec670>", "_build": "<function ActorCriticPolicy._build at 0x7b90846ec700>", "forward": "<function ActorCriticPolicy.forward at 0x7b90846ec790>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b90846ec820>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b90846ec8b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7b90846ec940>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b90846ec9d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b90846eca60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b90846ecaf0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b908487fa00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 500736, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1719078420477679435, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAOB9Ir6/nBc/Fd2DPRPmk740N8w8w+mNPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1956, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_shape": [8], "low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]", "high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]", "_np_random": "Generator(PCG64)"}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
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 sha256:8efb11725f834936df1133acc1cdb9c540634f9a296613298cae9d4862fd3186
|
3 |
+
size 147983
|
ppo-LunarLander-v2/data
CHANGED
@@ -4,34 +4,34 @@
|
|
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
|
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 |
-
"extract_features": "<function ActorCriticPolicy.extract_features at
|
14 |
-
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at
|
15 |
-
"_predict": "<function ActorCriticPolicy._predict at
|
16 |
-
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at
|
17 |
-
"get_distribution": "<function ActorCriticPolicy.get_distribution at
|
18 |
-
"predict_values": "<function ActorCriticPolicy.predict_values at
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
-
"_abc_impl": "<_abc._abc_data object at
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
-
"num_timesteps":
|
25 |
-
"_total_timesteps":
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
-
"start_time":
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
-
":serialized:": "
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -41,20 +41,20 @@
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
-
"_current_progress_remaining": -0.
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
-
":serialized:": "
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
-
"_n_updates":
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
-
":serialized:": "
|
58 |
"dtype": "float32",
|
59 |
"bounded_below": "[ True True True True True True True True]",
|
60 |
"bounded_above": "[ True True True True True True True True]",
|
@@ -69,7 +69,7 @@
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
-
":serialized:": "
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
|
|
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 0x7b90846ec4c0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b90846ec550>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b90846ec5e0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b90846ec670>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7b90846ec700>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7b90846ec790>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7b90846ec820>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b90846ec8b0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7b90846ec940>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b90846ec9d0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b90846eca60>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7b90846ecaf0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7b908487fa00>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 500736,
|
25 |
+
"_total_timesteps": 500000,
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1719078420477679435,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAOB9Ir6/nBc/Fd2DPRPmk740N8w8w+mNPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
41 |
"_episode_num": 0,
|
42 |
"use_sde": false,
|
43 |
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.0014719999999999178,
|
45 |
"_stats_window_size": 100,
|
46 |
"ep_info_buffer": {
|
47 |
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
},
|
50 |
"ep_success_buffer": {
|
51 |
":type:": "<class 'collections.deque'>",
|
52 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
},
|
54 |
+
"_n_updates": 1956,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
+
":serialized:": "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",
|
58 |
"dtype": "float32",
|
59 |
"bounded_below": "[ True True True True True True True True]",
|
60 |
"bounded_above": "[ True True True True True True True True]",
|
|
|
69 |
},
|
70 |
"action_space": {
|
71 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "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",
|
73 |
"n": "4",
|
74 |
"start": "0",
|
75 |
"_shape": [],
|
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 88362
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a007aca965c2177629757243448726f0c0a3cf1a9f2b753b2b974bb9060f5e6
|
3 |
size 88362
|
ppo-LunarLander-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ae26cbe1ba732aeb42fdb7908c105949fd21d7b33a313f8fddc1a55b17778d2
|
3 |
size 43762
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 213.39973808180875, "std_reward": 79.11609406936692, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-22T18:04:59.014758"}
|