hariduraibaskar
commited on
Commit
•
f2d9439
1
Parent(s):
a840924
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: 252.60 +/- 20.91
|
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 0x7dafed82ab00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7dafed82ab90>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7dafed82ac20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7dafed82acb0>", "_build": "<function ActorCriticPolicy._build at 0x7dafed82ad40>", "forward": "<function ActorCriticPolicy.forward at 0x7dafed82add0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7dafed82ae60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7dafed82aef0>", "_predict": "<function ActorCriticPolicy._predict at 0x7dafed82af80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7dafed82b010>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7dafed82b0a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7dafed82b130>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7dafed814400>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1699355518258079210, "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:": "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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:": "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "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 sha256:8a1fb44d30927fb2ab0c2011f02662b69b5bac49610cee3dde33fb53ec142194
|
3 |
+
size 148054
|
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 0x7dafed82ab00>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7dafed82ab90>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7dafed82ac20>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7dafed82acb0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7dafed82ad40>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7dafed82add0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7dafed82ae60>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7dafed82aef0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7dafed82af80>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7dafed82b010>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7dafed82b0a0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7dafed82b130>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7dafed814400>"
|
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": 1699355518258079210,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"_last_obs": {
|
33 |
+
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAJqZJL1cS2O6heR/N0W7yTKPkcw6Rm+WtgAAgD8AAIA/gMQtPc/hDT6OoJS9a0E1vsEMmDxCHJa9AAAAAAAAAABzxg6+pAdGu/KAyLqwScm3sT6HPMpC7TkAAIA/AACAP4Y1Zr6oUoC8bSrmOzIL5TlNquY9yhW5ugAAgD8AAIA/gBvcvSzPrjwgST+9P3JLvg0rGjyWXhu8AAAAAAAAAAAz9SI9XHN6ujmBJbzZO4s1vJglOboH/bQAAIA/AACAPxptLL2uwbK6pbGdOhVUCzUpRcs46RS0uQAAgD8AAIA/M318vOGYoLoAduc30gOjtrza6LmCBfi2AACAPwAAgD/NVDA76WxxvHK1v7oGnpg8h9PPPaZjdr0AAIA/AACAP5o6kDy4Poa5mBTNu6PdrzgfDKe7ix1rOgAAgD8AAIA/zdGrvexp9blW/jq7xtEFOGJz7Djded85AACAPwAAgD+aPRs8j1Z6ukudfTo9jTSzquhCuwVsVrMAAIA/AAAAAAC+1DyuMYW6be3uut7AXbU67ig6th0LOgAAgD8AAIA/5mthvVw7YbruiKW51YyctkwcYbnyFg42AACAPwAAgD8APfM89mRruqpU2DpEPDozCYpCu+L1+bkAAIA/AACAPwAGYbyuJ4a6Q03jOYeLUTbQ7yQ7PrhGNQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
|
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:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
|
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:": "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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:": "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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 sha256:1375ffb559aa4061454e8a1c64c63231f3215ec460511da2e9f501963028d141
|
3 |
+
size 88362
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3218c337db05a361a0ed408ceb8891a3eca6ba81f576c9361e76de0cafdd3525
|
3 |
+
size 43762
|
ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.1.0+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.23.5
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
ADDED
Binary file (196 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 252.5953446427042, "std_reward": 20.912241486044984, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-07T11:40:04.087577"}
|