Initial commit
Browse files- README.md +37 -0
- a2c-AntBulletEnv-v0.zip +3 -0
- a2c-AntBulletEnv-v0/_stable_baselines3_version +1 -0
- a2c-AntBulletEnv-v0/data +111 -0
- a2c-AntBulletEnv-v0/policy.optimizer.pth +3 -0
- a2c-AntBulletEnv-v0/policy.pth +3 -0
- a2c-AntBulletEnv-v0/pytorch_variables.pth +3 -0
- a2c-AntBulletEnv-v0/system_info.txt +9 -0
- config.json +1 -0
- results.json +1 -0
- vec_normalize.pkl +3 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- AntBulletEnv-v0
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: A2C
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: AntBulletEnv-v0
|
16 |
+
type: AntBulletEnv-v0
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 217.64 +/- 61.50
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **A2C** Agent playing **AntBulletEnv-v0**
|
25 |
+
This is a trained model of a **A2C** agent playing **AntBulletEnv-v0**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
+
|
28 |
+
## Usage (with Stable-baselines3)
|
29 |
+
TODO: Add your code
|
30 |
+
|
31 |
+
|
32 |
+
```python
|
33 |
+
from stable_baselines3 import ...
|
34 |
+
from huggingface_sb3 import load_from_hub
|
35 |
+
|
36 |
+
...
|
37 |
+
```
|
a2c-AntBulletEnv-v0.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8dae0c8a1a0a51f7c1c9a0b0b0cac501f59c94fafb6cb5ee8ee16206afec48ed
|
3 |
+
size 126782
|
a2c-AntBulletEnv-v0/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0
|
a2c-AntBulletEnv-v0/data
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
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 0x7f37541668b0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3754166940>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f37541669d0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3754166a60>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f3754166af0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f3754166b80>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3754166c10>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3754166ca0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f3754166d30>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3754166dc0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3754166e50>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3754166ee0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f37546079c0>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {
|
24 |
+
":type:": "<class 'dict'>",
|
25 |
+
":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu",
|
26 |
+
"log_std_init": -2,
|
27 |
+
"ortho_init": false,
|
28 |
+
"optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
|
29 |
+
"optimizer_kwargs": {
|
30 |
+
"alpha": 0.99,
|
31 |
+
"eps": 1e-05,
|
32 |
+
"weight_decay": 0
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"num_timesteps": 20000,
|
36 |
+
"_total_timesteps": 20000,
|
37 |
+
"_num_timesteps_at_start": 0,
|
38 |
+
"seed": null,
|
39 |
+
"action_noise": null,
|
40 |
+
"start_time": 1688358208298980408,
|
41 |
+
"learning_rate": 0.00096,
|
42 |
+
"tensorboard_log": null,
|
43 |
+
"_last_obs": {
|
44 |
+
":type:": "<class 'numpy.ndarray'>",
|
45 |
+
":serialized:": "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"
|
46 |
+
},
|
47 |
+
"_last_episode_starts": {
|
48 |
+
":type:": "<class 'numpy.ndarray'>",
|
49 |
+
":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
|
50 |
+
},
|
51 |
+
"_last_original_obs": {
|
52 |
+
":type:": "<class 'numpy.ndarray'>",
|
53 |
+
":serialized:": "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"
|
54 |
+
},
|
55 |
+
"_episode_num": 0,
|
56 |
+
"use_sde": true,
|
57 |
+
"sde_sample_freq": -1,
|
58 |
+
"_current_progress_remaining": 0.0,
|
59 |
+
"_stats_window_size": 100,
|
60 |
+
"ep_info_buffer": {
|
61 |
+
":type:": "<class 'collections.deque'>",
|
62 |
+
":serialized:": "gAWV+gMAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQCQPqkdmxt6MAWyUSxiMAXSUR0ATuALApKBedX2UKGgGR0A8ZT4L1EmZaAdLNWgIR0AUhRTCLuQZdX2UKGgGR0AXy+ajN6gNaAdLFGgIR0AUz6InBtUGdX2UKGgGR0AM0+7lJYknaAdLF2gIR0AVI6fapPykdX2UKGgGR0B+Ccuh9LHuaAdN6ANoCEdAISEf1YhdMXV9lChoBkdAeI3C3w1BMWgHTegDaAhHQCEhUNrj5sV1fZQoaAZHQHBte9WZJCloB03oA2gIR0AhIXqJMxoJdX2UKGgGRz/5ZDJEH+qBaAdLFmgIR0AhTByjpLVXdX2UKGgGR0AoE4FRpDeCaAdLLmgIR0AheMb3oLXudX2UKGgGR0ALThP0qYqoaAdLFGgIR0AhnXGwRoRJdX2UKGgGR0BpM57VrhzeaAdN6ANoCEdAIf97fHggo3V9lChoBkdAAa5n13+uNmgHSxRoCEdAIiRtYSxqwnV9lChoBke/6swL3K0UoWgHSxRoCEdAIkbsfJV81HV9lChoBkdAeu0ijL0SRWgHTegDaAhHQChAnfEXLvF1fZQoaAZHQHd24ePq9oNoB03oA2gIR0Aoaoc7yQPqdX2UKGgGR0B67UDcM3IdaAdN6ANoCEdAKL75mAbyY3V9lChoBkdAeHowgTyrgmgHTegDaAhHQClrVSXMQmN1fZQoaAZHP+zFspG4I8hoB0sUaAhHQCmP7SApazN1fZQoaAZHQHptTmOlwcZoB03oA2gIR0Avs7OE/SpjdX2UKGgGR0BzxhxT850baAdN6ANoCEdAL92+GoJiRXV9lChoBkdAMXyPuG9HtmgHSydoCEdAL/0tyxRl6XV9lChoBkdALELwe/5+IGgHSyNoCEdAMA+P/7zkIXV9lChoBkdAdaHZvDP4VWgHTegDaAhHQDAXsPatcOd1fZQoaAZHQCFb08NhE0BoB0smaAhHQDA6P4mCyyF1fZQoaAZHQHRMVfZ26kJoB03oA2gIR0AwgQyhzvJBdX2UKGgGR0BT3SMHbAUMaAdLpmgIR0Awl6po9LYgdX2UKGgGR0B5ZLX2/SH/aAdNrAJoCEdAMrb2QGOdXnV9lChoBkdAbDJG4I8hcWgHTdoCaAhHQDNEcp9ZzPt1fZQoaAZHQH6l1mBe5WloB03oA2gIR0AzuZgXuVopdX2UKGgGR0BySxM8HObBaAdN6ANoCEdANC7r5ZbILnV9lChoBkdAe6qQwsXizmgHTegDaAhHQDZvlJYkmhN1fZQoaAZHQH6BnHBDXvpoB03oA2gIR0A2/K1XvH94dWUu"
|
63 |
+
},
|
64 |
+
"ep_success_buffer": {
|
65 |
+
":type:": "<class 'collections.deque'>",
|
66 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
67 |
+
},
|
68 |
+
"_n_updates": 625,
|
69 |
+
"n_steps": 8,
|
70 |
+
"gamma": 0.99,
|
71 |
+
"gae_lambda": 0.9,
|
72 |
+
"ent_coef": 0.0,
|
73 |
+
"vf_coef": 0.4,
|
74 |
+
"max_grad_norm": 0.5,
|
75 |
+
"normalize_advantage": false,
|
76 |
+
"observation_space": {
|
77 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
78 |
+
":serialized:": "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",
|
79 |
+
"dtype": "float32",
|
80 |
+
"bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]",
|
81 |
+
"bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]",
|
82 |
+
"_shape": [
|
83 |
+
28
|
84 |
+
],
|
85 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
|
86 |
+
"high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf]",
|
87 |
+
"low_repr": "-inf",
|
88 |
+
"high_repr": "inf",
|
89 |
+
"_np_random": null
|
90 |
+
},
|
91 |
+
"action_space": {
|
92 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
93 |
+
":serialized:": "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",
|
94 |
+
"dtype": "float32",
|
95 |
+
"bounded_below": "[ True True True True True True True True]",
|
96 |
+
"bounded_above": "[ True True True True True True True True]",
|
97 |
+
"_shape": [
|
98 |
+
8
|
99 |
+
],
|
100 |
+
"low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
|
101 |
+
"high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
|
102 |
+
"low_repr": "-1.0",
|
103 |
+
"high_repr": "1.0",
|
104 |
+
"_np_random": null
|
105 |
+
},
|
106 |
+
"n_envs": 4,
|
107 |
+
"lr_schedule": {
|
108 |
+
":type:": "<class 'function'>",
|
109 |
+
":serialized:": "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"
|
110 |
+
}
|
111 |
+
}
|
a2c-AntBulletEnv-v0/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d7c0100a467827cc43ef29488d4b5b93c8d6c21abf3a734a4c373c1de4fe79c
|
3 |
+
size 56190
|
a2c-AntBulletEnv-v0/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:372e00cb70a0046131bfb98bdc0af86e3957747b83d3d74c597e949a7c313a23
|
3 |
+
size 56894
|
a2c-AntBulletEnv-v0/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
a2c-AntBulletEnv-v0/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.19.0-46-generic-x86_64-with-glibc2.35 # 47~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jun 21 15:35:31 UTC 2
|
2 |
+
- Python: 3.9.16
|
3 |
+
- Stable-Baselines3: 2.0.0
|
4 |
+
- PyTorch: 2.0.1+cu117
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.25.0
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.23.0
|
config.json
ADDED
@@ -0,0 +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 0x7f37541668b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3754166940>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f37541669d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3754166a60>", "_build": "<function ActorCriticPolicy._build at 0x7f3754166af0>", "forward": "<function ActorCriticPolicy.forward at 0x7f3754166b80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3754166c10>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3754166ca0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3754166d30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3754166dc0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3754166e50>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3754166ee0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f37546079c0>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", "log_std_init": -2, "ortho_init": false, "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 20000, "_total_timesteps": 20000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688358208298980408, "learning_rate": 0.00096, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVNQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJbAAQAAAAAAAH4CGb+FB5c9kKsoP4lzFr7CYbE+9avkPa9fkD8p++c9Gdg+P/XOSr5RQWA/V7Fyvb2LZ7+mX6E+4hGbP49Wcj0+3BW/70kdPUci2LyKFMM8lCdtPyb61bxFjAy/a2NZviujpj4feXC/42+UPhercz4254i/gKolP4mprj4dnqI+QlEfP0iXrz6WcqU/CT55Pr3vtj8sVui8eWBgP0xgIj3XvoC/S/zbPShMmz9SlI68pfATv7XbMT4wNpi8sHU9PTkSbj/+7Ge9pe9sv6+Tzr4ro6Y+H3lwv+NvlD4Xq3M+BFXnPpZPbz+fmpk8RB0KPqApXT92rpU+NLwwv7Lahz9Tj7Y/8OBYOzrdF78/qAY+ZdmiP/DsArywKIG/K6aDPQfNob4sEjk/56/pv264uj2eo2w/gcNhvfY1XL+GHo2+K6OmPh95cL/jb5Q+F6tzPiV4kL88Cwu/q08JP3zHZL6EpEI8lZQzPmluCL9LZdY/BZe2P6utS7y4XpC/OuLwvZL2GD93pwLAWSOBvyFikj1fvfU/T9gdPXN0gLwxAEc9LuCevyTpyjvIZG+/vMlNvSujpj4feXC/42+UPhercz6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLHIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 0, "use_sde": true, "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": 625, "n_steps": 8, "gamma": 0.99, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.4, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "_shape": [28], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVzwEAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAACAvwAAgL8AAIC/AACAvwAAgL8AAIC/AACAvwAAgL+UaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAgD8AAIA/AACAPwAAgD8AAIA/AACAPwAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjAQtMS4wlIwJaGlnaF9yZXBylIwDMS4wlIwKX25wX3JhbmRvbZROdWIu", "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": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.19.0-46-generic-x86_64-with-glibc2.35 # 47~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Jun 21 15:35:31 UTC 2", "Python": "3.9.16", "Stable-Baselines3": "2.0.0", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.25.0", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.23.0"}}
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 217.63591472599654, "std_reward": 61.4997926370169, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-02T21:37:13.764512"}
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:146ee5948b3fa6a3a374f7a4dac05595e7dacb8e72be485d1263fc3e58ced765
|
3 |
+
size 2376
|