floraxhuang
commited on
Commit
·
c7a1230
1
Parent(s):
82752aa
Upload PPO LunarLander-v2 trained agent
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +99 -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 +9 -0
- replay.mp4 +0 -0
- results.json +1 -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: 250.28 +/- 21.72
|
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 0x7fed03141fc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fed03142050>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fed031420e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fed03142170>", "_build": "<function ActorCriticPolicy._build at 0x7fed03142200>", "forward": "<function ActorCriticPolicy.forward at 0x7fed03142290>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fed03142320>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fed031423b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fed03142440>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fed031424d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fed03142560>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fed031425f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fed03148fc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688196263268462223, "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": -0.015808000000000044, "_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": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1519b62b60e04f1bf3775c49f2f1c4c707f57693e687c21bf57632c49263cd23
|
3 |
+
size 146755
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
ppo-LunarLander-v2/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 0x7fed03141fc0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fed03142050>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fed031420e0>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fed03142170>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7fed03142200>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7fed03142290>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7fed03142320>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fed031423b0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7fed03142440>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fed031424d0>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fed03142560>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7fed031425f0>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fed03148fc0>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1015808,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1688196263268462223,
|
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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
|
39 |
+
},
|
40 |
+
"_last_original_obs": null,
|
41 |
+
"_episode_num": 0,
|
42 |
+
"use_sde": false,
|
43 |
+
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.015808000000000044,
|
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": 248,
|
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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
|
73 |
+
"n": "4",
|
74 |
+
"start": "0",
|
75 |
+
"_shape": [],
|
76 |
+
"dtype": "int64",
|
77 |
+
"_np_random": null
|
78 |
+
},
|
79 |
+
"n_envs": 16,
|
80 |
+
"n_steps": 1024,
|
81 |
+
"gamma": 0.999,
|
82 |
+
"gae_lambda": 0.98,
|
83 |
+
"ent_coef": 0.01,
|
84 |
+
"vf_coef": 0.5,
|
85 |
+
"max_grad_norm": 0.5,
|
86 |
+
"batch_size": 64,
|
87 |
+
"n_epochs": 4,
|
88 |
+
"clip_range": {
|
89 |
+
":type:": "<class 'function'>",
|
90 |
+
":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
|
91 |
+
},
|
92 |
+
"clip_range_vf": null,
|
93 |
+
"normalize_advantage": true,
|
94 |
+
"target_kl": null,
|
95 |
+
"lr_schedule": {
|
96 |
+
":type:": "<class 'function'>",
|
97 |
+
":serialized:": "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"
|
98 |
+
}
|
99 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2bf72252cf4caad55468858f145eb8e1be1a8f37994a2b7f2465c17a7c6f641
|
3 |
+
size 87929
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd36ac2d563dc49df5929705286321e6652ac15153e4493b1d8179e7e905d78a
|
3 |
+
size 43329
|
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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.0.1+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
ADDED
Binary file (200 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 250.2750669712299, "std_reward": 21.72044343624545, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-01T07:50:20.926770"}
|