Upload LunarLander trained
Browse files- README.md +35 -1
- 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
CHANGED
@@ -1,3 +1,37 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 237.39 +/- 20.98
|
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 0x7f1d769f2ef0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1d769f2f80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1d769f3010>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1d769f30a0>", "_build": "<function ActorCriticPolicy._build at 0x7f1d769f3130>", "forward": "<function ActorCriticPolicy.forward at 0x7f1d769f31c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f1d769f3250>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1d769f32e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f1d769f3370>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1d769f3400>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1d769f3490>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1d769f3520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f1d769f5580>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1688617485659697212, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAFpRpj0UWI66h8zBOD57szMud4k65gjhtwAAgD8AAIA/+pkQPrTFXz/adjM+GWC7vlDNCD6iHae9AAAAAAAAAABmUBI8bviCvCtPeDs9Z5A8WynqvdJtaD0AAIA/AACAP9pslD2eML49njUUvvxn9r3FlRy9mZA4vQAAAAAAAAAAWge2PT2aOLlWF/6zmvMDrwIS9DWYVb4zAACAPwAAgD/SyIy+kfULP0znvz0POIG++SKbvf0Mez0AAAAAAAAAAGA7H74Le709nsmoPnawML4mbZY9joQAPAAAAAAAAAAAYH0oPiamjT9ePIw9Syihvt81wj3GvNu9AAAAAAAAAABzw549e7iEunvCGbQJv64uhwoCu9F/kjMAAIA/AACAP80ws7xQK40/XroHvMCkwr6WwZS8obanPQAAAAAAAAAAYMZHPjxNlD5hmD++0iKuvoxDa72iF2G8AAAAAAAAAACaUTq+MFbkPit5VD7gWY6+71H4PPRSAz4AAAAAAAAAAHP8tr24uKM+Xr/tPdJahr5sBQ49jtKLvQAAAAAAAAAAvXN4vsjWFD9BKyA+FFGHvvUql73409w9AAAAAAAAAACAc2a9rqHtusVoNzyekYw8NK21u6Xacz0AAIA/AACAP6aMur0p2G66gPUVuE3GH7PhVDg6GlsuNwAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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:": "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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": 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": "False", "Numpy": "1.25.0", "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:b2d63a8aca26487c5b29221025a4b190b79207dd895c2bf96d3e24f8af8f7836
|
3 |
+
size 146252
|
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 0x7f1d769f2ef0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1d769f2f80>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1d769f3010>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1d769f30a0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f1d769f3130>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f1d769f31c0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7f1d769f3250>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1d769f32e0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f1d769f3370>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1d769f3400>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1d769f3490>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1d769f3520>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7f1d769f5580>"
|
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": 1688617485659697212,
|
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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
|
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:": "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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 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69be37a6bbd977ed5d09ff2a51f12883fd284404afba7c4cbefd657ebcb8d085
|
3 |
+
size 87545
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62f8a792c904a892f6905402e8795233a91e03310f0b8966665cca156fb1a196
|
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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: False
|
6 |
+
- Numpy: 1.25.0
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
ADDED
Binary file (190 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 237.39435410000002, "std_reward": 20.983356838049723, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-06T04:54:23.914846"}
|