Upload PPO LunarLander-V2i,second agent trained agent from unit 1
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-LunarLander-V2i.zip +3 -0
- ppo-LunarLander-V2i/_stable_baselines3_version +1 -0
- ppo-LunarLander-V2i/data +99 -0
- ppo-LunarLander-V2i/policy.optimizer.pth +3 -0
- ppo-LunarLander-V2i/policy.pth +3 -0
- ppo-LunarLander-V2i/pytorch_variables.pth +3 -0
- ppo-LunarLander-V2i/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: 262.33 +/- 15.50
|
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 0x7c154c15b130>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c154c15b1c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c154c15b250>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c154c15b2e0>", "_build": "<function ActorCriticPolicy._build at 0x7c154c15b370>", "forward": "<function ActorCriticPolicy.forward at 0x7c154c15b400>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c154c15b490>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c154c15b520>", "_predict": "<function ActorCriticPolicy._predict at 0x7c154c15b5b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c154c15b640>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c154c15b6d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c154c15b760>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c154c15db40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1691731310097726587, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAOYWjb20R18/RMKTvRrn577yg9u9vVp0vAAAAAAAAAAAc5PYPWJhjD8ATxs+YwECvyb0FD4nAAo7AAAAAAAAAACA6wq9CGmOP617obswFf++X8qgvciOz7wAAAAAAAAAANMAeT72BJ0/uoqwPvIq9b4VMbE+nmSjPQAAAAAAAAAAWv4ivg/Efz/Q0WK+goILv0GhlL7DkzE9AAAAAAAAAACAt7g90LFpP1tmIT3O8cq+61oUPo17FL0AAAAAAAAAAIBrmz1yEp0/IpO3PiTu+r7wyL49bq2IPgAAAAAAAAAAZuLuu3vAjrrF3A84M04GM6HFJ7suHCe3AACAPwAAgD/NELI8AuklPk5DQrvjq3e+AMiZPDeGhbsAAAAAAAAAABq2gL2PzmK6HsmLORyjdzSt2EQ6GsqjuAAAgD8AAIA/zfMcvSl4ILqGXZM5vqbFNGlx0TrGy6e4AACAPwAAgD8mnEA+sUOXP2L91j5DN9O+MY2jPlLKaD4AAAAAAAAAAGaCs7tF7QM+o+fUvZHUlL5vQgi9YY9EvQAAAAAAAAAAAPjmvPbUMbqWoTA6RG5KNV9fxLnou0m5AACAPwAAgD9m4be9rXnIPu5fhz58pae+7xICPoKKgr0AAAAAAAAAAM3kWrzDyVO65OktOqux9LjYecm6erk/uQAAgD8AAIA/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": 310, "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": 5, "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-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
|
ppo-LunarLander-V2i.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cc6f58eadf4b4d21ef2417cfa36a7830bc712337844b06f498a860a47f0632b
|
3 |
+
size 146722
|
ppo-LunarLander-V2i/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
ppo-LunarLander-V2i/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 0x7c154c15b130>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c154c15b1c0>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c154c15b250>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c154c15b2e0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7c154c15b370>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7c154c15b400>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x7c154c15b490>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c154c15b520>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7c154c15b5b0>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c154c15b640>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c154c15b6d0>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7c154c15b760>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x7c154c15db40>"
|
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": 1691731310097726587,
|
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:": "gAWVKgwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHF4jM3ZPEeMAWyUS+aMAXSUR0C2MuSzkZJkdX2UKGgGR0BxK2717IDHaAdNAAFoCEdAtjLw8HObAnV9lChoBkdAcmitA9mpVGgHTQ4BaAhHQLYzIyAxzq91fZQoaAZHQHDhJr1uivhoB01dAWgIR0C2MytpItlJdX2UKGgGR0By4pxwQ176aAdL52gIR0C2M1fw3HaOdX2UKGgGR0BxZ9j2Bas7aAdNCAFoCEdAtjONSeiBXnV9lChoBkdAbv5iw0O3D2gHTQ0BaAhHQLYzopPAO8V1fZQoaAZHQHIPV09yLhtoB00YAWgIR0C2M7bgwXZXdX2UKGgGR0Byh0RVZLZjaAdNPAFoCEdAtjP2YIBzWHV9lChoBkdAcOICoS+QEWgHTSYBaAhHQLY0BRJmNBF1fZQoaAZHQHDy3WFvhqFoB008AWgIR0C2NCJkoWpIdX2UKGgGR0ByswNjLB9DaAdNAQFoCEdAtjQ7PIGQjnV9lChoBkdAcu9UbkwN9mgHTTEBaAhHQLY0b9eyAx11fZQoaAZHQHFSsYMvysloB003AWgIR0C2NKFI/Z/TdX2UKGgGR0BwaQ1rIo3KaAdNGAFoCEdAtjSpjZtelnV9lChoBkdAbCq619fCymgHTYkBaAhHQLY0rRradtl1fZQoaAZHQHEQzB/I8yNoB00qAWgIR0C2NQDPWxyGdX2UKGgGR0By1H5j6N2laAdNBgFoCEdAtjUU8SwnpnV9lChoBkdAbd29s7+1jWgHS/xoCEdAtjVDJiiItXV9lChoBkdATBWuPmxMWWgHS65oCEdAtjVUer+5v3V9lChoBkdAbfeWldkauWgHTTQBaAhHQLY1ekupS751fZQoaAZHQHDGie/YapBoB00JAWgIR0C2NckJSiuddX2UKGgGR0BwyDDiwSrYaAdNGgFoCEdAtjYTHEMspXV9lChoBkdAcX6ZRsMy8GgHTT4BaAhHQLY2NK5kK/p1fZQoaAZHQHFgeLNwBHVoB0vvaAhHQLY2Wf+jua51fZQoaAZHQG5Qf1pTMq1oB00GAWgIR0C2Nm2o3rD7dX2UKGgGR0Bx0tg3Lmp3aAdNJwFoCEdAtjaaFWXC0nV9lChoBkdAbVgxs2vSt2gHTQABaAhHQLY3EaWom5V1fZQoaAZHQHAgpDE3sHBoB00eAWgIR0C2Nx7rcCYDdX2UKGgGR0Bx4sUEgW8AaAdL6GgIR0C2N1yP2f03dX2UKGgGR0ANQi5d4VynaAdL0mgIR0C2N2qz3RG+dX2UKGgGR0Bu9Sdc0LtvaAdL5mgIR0C2N3BUedTYdX2UKGgGR0By4zg2qDK6aAdNLQFoCEdAtjeqWAwwkHV9lChoBkdAbzDy7wrlNmgHS+9oCEdAtjfWE+Pik3V9lChoBkdAb/Go3Jgb62gHTSEBaAhHQLY5IHbRF7V1fZQoaAZHQHOQd8JD3M9oB00OAWgIR0C2OUcFyJbddX2UKGgGR0BxE4t+TeO5aAdNAwFoCEdAtjl9dv863nV9lChoBkdActwdKNAC4mgHTQkBaAhHQLY5sL/0dzZ1fZQoaAZHQEcDUipvP1NoB0veaAhHQLY59aGYa5x1fZQoaAZHQHIk2XTmW+poB00OAWgIR0C2Of8IqsltdX2UKGgGR0BymHSJCSieaAdNgwFoCEdAtjoMpYs/ZHV9lChoBkdAch1CuU2UCGgHTQcBaAhHQLZBkqPOpsJ1fZQoaAZHQHBj5BLPD51oB00BAWgIR0C2QZLJ4jbBdX2UKGgGR0BwzsHRkVesaAdNHAFoCEdAtkHHwZwXInV9lChoBkdAcXJ5TIeYD2gHTZ4BaAhHQLZB5rWiDdx1fZQoaAZHQHB1MeXAuZloB00WAWgIR0C2QenUH6dldX2UKGgGR0Bw1PtpmEoOaAdNTAFoCEdAtkJ8J5VwP3V9lChoBkdAb5sDq4YrKGgHTQABaAhHQLZC6aOPvKF1fZQoaAZHQHGKNYW+GoJoB0v1aAhHQLZC8aPS2IB1fZQoaAZHQHFR5RXOnl5oB0vyaAhHQLZDGvHtF8Z1fZQoaAZHQG3qRHPNVzZoB00yAWgIR0C2QyLvsqrjdX2UKGgGR0ByefAHmig1aAdNNQFoCEdAtkNANZvDQHV9lChoBkdAbT28oQWepWgHTQUBaAhHQLZDVg88s+V1fZQoaAZHQFL9KCg9NetoB03oA2gIR0C2Q29VrAP/dX2UKGgGR0Bwp6KKpDNRaAdNHQFoCEdAtkN8STQmeHV9lChoBkdAbxwyAxzq8mgHS+NoCEdAtkOFYs/Y8XV9lChoBkdAceQrGR3eN2gHTRkBaAhHQLZD5X7cfvF1fZQoaAZHQHGck5+6RQtoB00KAWgIR0C2RBmSZBszdX2UKGgGR0BwmWvs7dSEaAdNJAFoCEdAtkRN0wJw9HV9lChoBkdAcU3eCkGiYmgHTTcBaAhHQLZEVs189fV1fZQoaAZHQHCzdCNS619oB02gAmgIR0C2RLjIq9XcdX2UKGgGR0BxabLW7OE/aAdNHAFoCEdAtkTCJuVHF3V9lChoBkdARvaBkI5YHWgHS7ZoCEdAtkTfeN1hcHV9lChoBkdAcj1rEcbR4WgHTQgBaAhHQLZE8jQAuI11fZQoaAZHQHBfbkKeCkJoB00OAWgIR0C2RQJwOvt/dX2UKGgGR0ByZOQdS2piaAdNAAFoCEdAtkUH5vcafnV9lChoBkdActp/tY0VJ2gHTQABaAhHQLZFDFBIFvB1fZQoaAZHQHKajHbRF7VoB0v4aAhHQLZFE88cMmZ1fZQoaAZHQFQ7yBClabFoB03oA2gIR0C2RTWOp84QdX2UKGgGR0BwMl1PnB+GaAdNBwFoCEdAtkVQbo8p1HV9lChoBkdAcZpI68xsVWgHTRcBaAhHQLZFVdIXj2l1fZQoaAZHQHIub+cYqG1oB00TAWgIR0C2RWvViF0xdX2UKGgGR0Bxo9jEvTPTaAdL82gIR0C2RZBoduHfdX2UKGgGR0ByEdFocrAhaAdNAQFoCEdAtkX95le4TnV9lChoBkdAch+o11nuiWgHTRsBaAhHQLZGJVawD/51fZQoaAZHQHDfGrXDm8xoB01DAWgIR0C2RkPvrnkldX2UKGgGR0BwgE4cWCVbaAdL7mgIR0C2RmHi3ocJdX2UKGgGR0Bx7nSE12q2aAdL9GgIR0C2Rn78m8dxdX2UKGgGR0BxzKcz67/XaAdL82gIR0C2RpVS88LbdX2UKGgGR0Bu2/Yao/A1aAdNIAFoCEdAtkahFz+3pnV9lChoBkdAcs3ej2zv7WgHTQABaAhHQLZGp8U21lZ1fZQoaAZHQHHckqx1PnBoB00AAWgIR0C2RrF7x/d7dX2UKGgGR0BxqlsqJ/G3aAdNLwFoCEdAtkazFxXGO3V9lChoBkdAc5JpTMqz7mgHS+xoCEdAtkbaCg9Ne3V9lChoBkdAcCz1m8M/hWgHS+JoCEdAtkbja37UG3V9lChoBkdAcGQljEvTPWgHTSABaAhHQLZHDJYT0xx1fZQoaAZHQHFEilN1yNpoB00TAWgIR0C2RxOhkAggdX2UKGgGR0BtZ/+uNgjRaAdL9GgIR0C2Ry2ig00ndX2UKGgGR0Busb7Kq4pdaAdNXwFoCEdAtkdSgK4QSXV9lChoBkdAcBkRbr1M/WgHTQUBaAhHQLZH5IKtxMp1fZQoaAZHQHGJ0TQE6ktoB0vvaAhHQLZICYzzmOl1fZQoaAZHQG+c01IiC8RoB0v4aAhHQLZISw6ySmt1fZQoaAZHQHDFWbLEDQtoB01PAWgIR0C2SOIC+10DdX2UKGgGR0ByxDnyNGViaAdL8mgIR0C2SPqZ+hGpdX2UKGgGR0BxnfKifxtpaAdNHQFoCEdAtkkY4wRGt3V9lChoBkdAb6QqGUOd5WgHTRcBaAhHQLZJGQmeDnN1fZQoaAZHQHMcUGNaQmxoB0v6aAhHQLZJIUXHim51fZQoaAZHQHQGlGsmv4doB00tAWgIR0C2SSkh3aBadX2UKGgGR0ByZiMS9M9KaAdNQAFoCEdAtkk73bmEG3V9lChoBkdAcmNJnQID5mgHTTUBaAhHQLZJYsHSncd1ZS4="
|
49 |
+
},
|
50 |
+
"ep_success_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
53 |
+
},
|
54 |
+
"_n_updates": 310,
|
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": 5,
|
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-V2i/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65eb4ea1ee230afa9b7cfef8789baf580f7f9c12033c81206648f80ecba55634
|
3 |
+
size 87929
|
ppo-LunarLander-V2i/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d054282efd61a2f9339d57b3116d3e5b857a63dc02d6ad885f561211b4fa2d97
|
3 |
+
size 43329
|
ppo-LunarLander-V2i/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-V2i/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 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: 1.23.5
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
replay.mp4
ADDED
Binary file (161 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 262.3264022581425, "std_reward": 15.499904242881927, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-11T05:46:42.568806"}
|