Upload PPO LunarLander-v2 trained agent
Browse files- .gitattributes +1 -0
- README.md +36 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +94 -0
- ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2/policy.pth +3 -0
- ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2/system_info.txt +7 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 266.16 +/- 21.16
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
26 |
+
|
27 |
+
## Usage (with Stable-baselines3)
|
28 |
+
TODO: Add your code
|
29 |
+
|
30 |
+
|
31 |
+
```python
|
32 |
+
from stable_baselines3 import ...
|
33 |
+
from huggingface_sb3 import load_from_hub
|
34 |
+
|
35 |
+
...
|
36 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f69f2d47dd0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f69f2d47e60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f69f2d47ef0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f69f2d47f80>", "_build": "<function ActorCriticPolicy._build at 0x7f69f2cce050>", "forward": "<function ActorCriticPolicy.forward at 0x7f69f2cce0e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f69f2cce170>", "_predict": "<function ActorCriticPolicy._predict at 0x7f69f2cce200>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f69f2cce290>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f69f2cce320>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f69f2cce3b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f69f2d16900>"}, "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////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": 1653503580.9081612, "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:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 368, "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": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:790b6b40d9bffede1e3f685a62d9e57de7bc3abcf4df46167891662454977891
|
3 |
+
size 144178
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
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 0x7f69f2d47dd0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f69f2d47e60>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f69f2d47ef0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f69f2d47f80>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f69f2cce050>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f69f2cce0e0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f69f2cce170>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f69f2cce200>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f69f2cce290>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f69f2cce320>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f69f2cce3b0>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f69f2d16900>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "gASVwwEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBVudW1weS5jb3JlLm11bHRpYXJyYXmUjAxfcmVjb25zdHJ1Y3SUk5RoBowHbmRhcnJheZSTlEsAhZRDAWKUh5RSlChLAUsIhZRoColDIAAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/lHSUYowEaGlnaJRoEmgUSwCFlGgWh5RSlChLAUsIhZRoColDIAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/lHSUYowNYm91bmRlZF9iZWxvd5RoEmgUSwCFlGgWh5RSlChLAUsIhZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDCAAAAAAAAAAAlHSUYowNYm91bmRlZF9hYm92ZZRoEmgUSwCFlGgWh5RSlChLAUsIhZRoKolDCAAAAAAAAAAAlHSUYowKX25wX3JhbmRvbZROdWIu",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 1507328,
|
46 |
+
"_total_timesteps": 1500000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1653503580.9081612,
|
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:": "gASVjQIAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxBLCIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUIAAgAAs2H/PWBXiT9MhwI+3UG+vrjbFT5gMQE9AAAAAAAAAACmhdE9rt2culVo3DoNs4A1CMSyOrAI/rkAAAAAAACAP2Zc8zx7oqy6La/LOTaVGLaR4n46ntPouAAAgD8AAIA/M4nOvNw0dbyS6Gm8ZwHZPOYo2T2GS6y9AACAPwAAgD9N8SS9hUvcON54QzoEMy016SVau1tcZ7kAAIA/AACAP9XfiL76w0Y+FptUPl5twb7LVxa+SHVDPQAAAAAAAAAAGmggvVxzGrpRJYM5L1jNM1N9VLvXGZu4AACAPwAAgD8zXUu9nxT8u5TkMzxct6M8KQ9Hvc9biD0AAIA/AACAP2Y7yD0pRD+6Kik1uNp9YLPW1HE7VY5VNwAAgD8AAIA/s9MBPd9KyTyrJHo+Udwtvvxoqz2+RIY9AAAAAAAAAADt2xm+47UEPb1Cpz2PdX6+Q7+tvW4n2DwAAAAAAAAAAAAXEj2XW24+zqO2vbLloL7/URG9evoHPAAAAAAAAAAADYkSPnbHlT9ZB8s+G1ywvi3XWD5uMAw+AAAAAAAAAADabbs9TlmIPeV7T779wJK+4TwCvTwaBz0AAAAAAAAAAOZLHz1IJ4e6knMYNMMCtC/GXnC6gk25swAAgD8AAIA/AD+YPNdlLrvuqCY73N+HPIjqTbxi9Go9AACAPwAAgD+UdJRiLg=="
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.004885333333333408,
|
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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 368,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
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,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0704a65661d922acc0a92264ab60bff63ec80d944ac47a625c06f8fa99dfaee
|
3 |
+
size 84893
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba168c887e732534c564508f8b3b5c3f21ab6dfbbba19b2246db6959647027d0
|
3 |
+
size 43201
|
ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61e89aaf07d5ead8512e0260b888acd5de57bef25ba7c4db816548f91fadb5ef
|
3 |
+
size 226832
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 266.1613481659514, "std_reward": 21.159551715881943, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-25T19:16:01.376318"}
|