CoderMan-O
commited on
Commit
•
e865144
1
Parent(s):
9504e44
Upload PPO BipedalWalker-v3 trained agent
Browse files- BipedalWalker-v3.zip +2 -2
- BipedalWalker-v3/data +20 -20
- BipedalWalker-v3/policy.optimizer.pth +1 -1
- BipedalWalker-v3/policy.pth +1 -1
- README.md +1 -1
- config.json +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
BipedalWalker-v3.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:ff062d45a3583ba2b9547986ffa674c7c31c29d29779addf595bf8abfc22432b
|
3 |
+
size 174885
|
BipedalWalker-v3/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
|
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": {},
|
@@ -26,16 +26,16 @@
|
|
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'>",
|
38 |
-
":serialized:": "
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
@@ -45,13 +45,13 @@
|
|
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:": "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",
|
@@ -82,8 +82,8 @@
|
|
82 |
"high_repr": "1.0",
|
83 |
"_np_random": null
|
84 |
},
|
85 |
-
"n_envs":
|
86 |
-
"n_steps":
|
87 |
"gamma": 0.999,
|
88 |
"gae_lambda": 0.98,
|
89 |
"ent_coef": 0.01,
|
|
|
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 0x7e44215bf370>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e44215bf400>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e44215bf490>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e44215bf520>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7e44215bf5b0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7e44215bf640>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7e44215bf6d0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e44215bf760>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7e44215bf7f0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e44215bf880>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e44215bf910>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7e44215bf9a0>",
|
19 |
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7e44215b5b00>"
|
21 |
},
|
22 |
"verbose": 1,
|
23 |
"policy_kwargs": {},
|
|
|
26 |
"_num_timesteps_at_start": 0,
|
27 |
"seed": null,
|
28 |
"action_noise": null,
|
29 |
+
"start_time": 1714371526142972584,
|
30 |
"learning_rate": 0.0003,
|
31 |
"tensorboard_log": null,
|
32 |
"_last_obs": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "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"
|
35 |
},
|
36 |
"_last_episode_starts": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
|
39 |
},
|
40 |
"_last_original_obs": null,
|
41 |
"_episode_num": 0,
|
|
|
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": 400,
|
55 |
"observation_space": {
|
56 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
57 |
":serialized:": "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",
|
|
|
82 |
"high_repr": "1.0",
|
83 |
"_np_random": null
|
84 |
},
|
85 |
+
"n_envs": 4,
|
86 |
+
"n_steps": 500,
|
87 |
"gamma": 0.999,
|
88 |
"gae_lambda": 0.98,
|
89 |
"ent_coef": 0.01,
|
BipedalWalker-v3/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 105121
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8998e9fabdadcd3d33ac6c6512ba4d97a8ceaffefb9d238575987e6c0b01f74
|
3 |
size 105121
|
BipedalWalker-v3/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 52143
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eeca3e9b07760fb4d702699798bdc469b09cc1c147682bf1a8cedcde2695954
|
3 |
size 52143
|
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: BipedalWalker-v3
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: BipedalWalker-v3
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: -58.54 +/- 86.20
|
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 0x7e38025c36d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e38025c3760>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e38025c37f0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e38025c3880>", "_build": "<function ActorCriticPolicy._build at 0x7e38025c3910>", "forward": "<function ActorCriticPolicy.forward at 0x7e38025c39a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e38025c3a30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e38025c3ac0>", "_predict": "<function ActorCriticPolicy._predict at 0x7e38025c3b50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e38025c3be0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e38025c3c70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e38025c3d00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e380255dec0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 200000, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1714107195666948021, "learning_rate": 0.0003, "tensorboard_log": null, "_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": 0.0, "_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": 1000, "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 True True True True\n True True True True True True True True True True True True]", "bounded_above": "[ True True True True True True True True True True True True\n True True True True True True True True True True True True]", "_shape": [24], "low": "[-3.1415927 -5. -5. -5. -3.1415927 -5.\n -3.1415927 -5. -0. -3.1415927 -5. -3.1415927\n -5. -0. -1. -1. -1. -1.\n -1. -1. -1. -1. -1. -1. ]", "high": "[3.1415927 5. 5. 5. 3.1415927 5. 3.1415927\n 5. 5. 3.1415927 5. 3.1415927 5. 5.\n 1. 1. 1. 1. 1. 1. 1.\n 1. 1. 1. ]", "low_repr": "[-3.1415927 -5. -5. -5. -3.1415927 -5.\n -3.1415927 -5. -0. -3.1415927 -5. -3.1415927\n -5. -0. -1. -1. -1. -1.\n -1. -1. -1. -1. -1. -1. ]", "high_repr": "[3.1415927 5. 5. 5. 3.1415927 5. 3.1415927\n 5. 5. 3.1415927 5. 3.1415927 5. 5.\n 1. 1. 1. 1. 1. 1. 1.\n 1. 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True]", "bounded_above": "[ True True True True]", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 16, "n_steps": 125, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "False", "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 0x7e44215bf370>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e44215bf400>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e44215bf490>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e44215bf520>", "_build": "<function ActorCriticPolicy._build at 0x7e44215bf5b0>", "forward": "<function ActorCriticPolicy.forward at 0x7e44215bf640>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e44215bf6d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e44215bf760>", "_predict": "<function ActorCriticPolicy._predict at 0x7e44215bf7f0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e44215bf880>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e44215bf910>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e44215bf9a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e44215b5b00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 200000, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1714371526142972584, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_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": 400, "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 True True True True\n True True True True True True True True True True True True]", "bounded_above": "[ True True True True True True True True True True True True\n True True True True True True True True True True True True]", "_shape": [24], "low": "[-3.1415927 -5. -5. -5. -3.1415927 -5.\n -3.1415927 -5. -0. -3.1415927 -5. -3.1415927\n -5. -0. -1. -1. -1. -1.\n -1. -1. -1. -1. -1. -1. ]", "high": "[3.1415927 5. 5. 5. 3.1415927 5. 3.1415927\n 5. 5. 3.1415927 5. 3.1415927 5. 5.\n 1. 1. 1. 1. 1. 1. 1.\n 1. 1. 1. ]", "low_repr": "[-3.1415927 -5. -5. -5. -3.1415927 -5.\n -3.1415927 -5. -0. -3.1415927 -5. -3.1415927\n -5. -0. -1. -1. -1. -1.\n -1. -1. -1. -1. -1. -1. ]", "high_repr": "[3.1415927 5. 5. 5. 3.1415927 5. 3.1415927\n 5. 5. 3.1415927 5. 3.1415927 5. 5.\n 1. 1. 1. 1. 1. 1. 1.\n 1. 1. 1. ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True]", "bounded_above": "[ True True True True]", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "n_steps": 500, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": -58.536842882012934, "std_reward": 86.19811885320128, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-29T06:26:57.227839"}
|