KlausFreitag
commited on
Commit
•
e665ce5
1
Parent(s):
f3cdb89
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
- test.zip +3 -0
- test/_stable_baselines3_version +1 -0
- test/data +99 -0
- test/policy.optimizer.pth +3 -0
- test/policy.pth +3 -0
- test/pytorch_variables.pth +3 -0
- test/system_info.txt +9 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- LunarLander-v2
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: LunarLander-v2
|
16 |
+
type: LunarLander-v2
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 159.13 +/- 121.24
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **PPO** Agent playing **LunarLander-v2**
|
25 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
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 |
+
```
|
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 0x7c3bba167880>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c3bba167910>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c3bba1679a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c3bba167a30>", "_build": "<function ActorCriticPolicy._build at 0x7c3bba167ac0>", "forward": "<function ActorCriticPolicy.forward at 0x7c3bba167b50>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c3bba167be0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c3bba167c70>", "_predict": "<function ActorCriticPolicy._predict at 0x7c3bba167d00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c3bba167d90>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c3bba167e20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c3bba167eb0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c3bba2ffc80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 200704, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709980022552180769, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAE1kej7pCQQ9PeHXOXkcyDjOxpU+5CgsuQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 980, "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": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
replay.mp4
ADDED
Binary file (131 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 159.1280345, "std_reward": 121.2429530367376, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-09T10:48:41.453573"}
|
test.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6629150d1dc99429816978782ef91e20b2cb288c2c3a78fd51ceaacd7c63f32c
|
3 |
+
size 147417
|
test/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
test/data
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7c3bba167880>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c3bba167910>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c3bba1679a0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c3bba167a30>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7c3bba167ac0>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7c3bba167b50>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7c3bba167be0>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c3bba167c70>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7c3bba167d00>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c3bba167d90>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c3bba167e20>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7c3bba167eb0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7c3bba2ffc80>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 200704,
|
25 |
+
"_total_timesteps": 200000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1709980022552180769,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"_last_obs": {
|
33 |
+
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAE1kej7pCQQ9PeHXOXkcyDjOxpU+5CgsuQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
35 |
+
},
|
36 |
+
"_last_episode_starts": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
39 |
+
},
|
40 |
+
"_last_original_obs": null,
|
41 |
+
"_episode_num": 0,
|
42 |
+
"use_sde": false,
|
43 |
+
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.0035199999999999676,
|
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": 980,
|
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]",
|
61 |
+
"_shape": [
|
62 |
+
8
|
63 |
+
],
|
64 |
+
"low": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
65 |
+
"high": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
66 |
+
"low_repr": "[-90. -90. -5. -5. -3.1415927 -5.\n -0. -0. ]",
|
67 |
+
"high_repr": "[90. 90. 5. 5. 3.1415927 5.\n 1. 1. ]",
|
68 |
+
"_np_random": null
|
69 |
+
},
|
70 |
+
"action_space": {
|
71 |
+
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
72 |
+
":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": null
|
78 |
+
},
|
79 |
+
"n_envs": 1,
|
80 |
+
"n_steps": 2048,
|
81 |
+
"gamma": 0.99,
|
82 |
+
"gae_lambda": 0.95,
|
83 |
+
"ent_coef": 0.0,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 10,
|
88 |
+
"clip_range": {
|
89 |
+
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "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"
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null,
|
95 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
98 |
+
}
|
99 |
+
}
|
test/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79a5365f11138c9e36528b7c9eacf2a15270a75be9755ba30de2a5e72ce40d59
|
3 |
+
size 88362
|
test/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19ff0fd1bfa587320be3c45ecc6e393d3f943f3b87b17d107397eba1dacdbd8f
|
3 |
+
size 43762
|
test/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
test/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.1.0+cu121
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.25.2
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|