Trained on local device
Browse files- README.md +37 -0
- config.json +1 -0
- ppo-lunar-lander-v2.zip +3 -0
- ppo-lunar-lander-v2/_stable_baselines3_version +1 -0
- ppo-lunar-lander-v2/data +99 -0
- ppo-lunar-lander-v2/policy.optimizer.pth +3 -0
- ppo-lunar-lander-v2/policy.pth +3 -0
- ppo-lunar-lander-v2/pytorch_variables.pth +3 -0
- ppo-lunar-lander-v2/system_info.txt +8 -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: 256.38 +/- 20.32
|
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 0x1237bcaf0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1237bcb80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1237bcc10>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1237bcca0>", "_build": "<function ActorCriticPolicy._build at 0x1237bcd30>", "forward": "<function ActorCriticPolicy.forward at 0x1237bcdc0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x1237bce50>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1237bcee0>", "_predict": "<function ActorCriticPolicy._predict at 0x1237bcf70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1237bd000>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x1237bd090>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x1237bd120>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x1237b3200>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1701356632154613000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGY3TT5umLA9umdavk2xs71XRBC9xaV7PQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVPgwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQG83jeKsMiOMAWyUTSACjAF0lEdAcgjzDGcWkHV9lChoBkdAb3AGFi8WbmgHTbcBaAhHQHIMDBEa2nd1fZQoaAZHQHAYkEC/47BoB00sAWgIR0ByDPjQzDXOdX2UKGgGR0Bw4mMir1dxaAdNNAFoCEdAcg3bUgB91HV9lChoBkdAcTUe5nUUf2gHTTIBaAhHQHIQuxOclPd1fZQoaAZHQDFSJ/G2kSFoB0u7aAhHQHIRSon8baR1fZQoaAZHQHEUfwiJO35oB00/AWgIR0ByEkt29tdidX2UKGgGR0BwVxu+AVfvaAdNUAJoCEdAchYBJI1+AnV9lChoBkc/53xlQMx46mgHS7xoCEdAchaR9PUKA3V9lChoBkdAcVppXp4bCWgHTTMBaAhHQHIXhgeA/cF1fZQoaAZHQHEoOxW1c+toB008AWgIR0ByGjWnTAnEdX2UKGgGR0Btk34ubqhUaAdNggFoCEdAchtmWdEsrnV9lChoBkdAcGDbp/wy7GgHTR0BaAhHQHIcTQ3PzFx1fZQoaAZHQHA5nOnl4khoB01nAWgIR0ByHxfgJkXldX2UKGgGR0BzSlt3wCr+aAdNUAFoCEdAciAmGdqcmXV9lChoBkdAbPekqtozvmgHTToBaAhHQHIhHj2i+L51fZQoaAZHwDKdfCyhSLtoB0vaaAhHQHIhx4Uvf0p1fZQoaAZHQHDI0Ja7mMhoB01VAWgIR0ByJKwbEP1+dX2UKGgGR0Bs+71h9b5eaAdNowFoCEdAciX4wh4dIXV9lChoBkdAbIolqrR0EGgHTREBaAhHQHImzebd8At1fZQoaAZHQHABA4S6DoRoB01YAWgIR0ByKa0ojOcEdX2UKGgGR0BuUIxzq8lHaAdNIwFoCEdAciqeWfK6nXV9lChoBkdAcK4fBvaURmgHTWsBaAhHQHIrv8dgfEJ1fZQoaAZHQGIWQTdtVJdoB03oA2gIR0ByMMSyt3fRdX2UKGgGR0ByEZaOgg5jaAdNoQFoCEdAcjPlsxfv4XV9lChoBkdAaztljEvTPWgHTfIBaAhHQHI1ZHmRvFZ1fZQoaAZHQHLr1ZLZi/hoB02HAWgIR0ByOGRA8jiXdX2UKGgGR0BxKuGIsRQKaAdNQAFoCEdAcjlQtSQ5m3V9lChoBkdAcdowz+FUQ2gHTXMBaAhHQHI6fechC+l1fZQoaAZHQHAHE0m+j/NoB010AWgIR0ByPdYeT3ZgdX2UKGgGR0BwiXIbOu7paAdNawFoCEdAcj76iCaqj3V9lChoBkdAcK5TaCcwxmgHTS8BaAhHQHI/5SrHU+d1fZQoaAZHQG6/jqOcUdtoB00pAWgIR0ByQnq+rU9ZdX2UKGgGR0Bw29t/FzdUaAdNfQFoCEdAckOWj4593XV9lChoBkdAbn/qmj0tiGgHTScBaAhHQHJEe58Sf191fZQoaAZHQHFYzkuHvc9oB019AWgIR0ByR1/6O5rhdX2UKGgGR0Bx3jZlFtsOaAdNSQFoCEdAckhf+0gKW3V9lChoBkdAblDdNWU8m2gHTSsBaAhHQHJJSb+cYqJ1fZQoaAZHQHB1F6E8JUpoB02IAWgIR0ByTGKm8/UwdX2UKGgGR0BwlQXTEzfraAdNuQFoCEdAck252yLQ5XV9lChoBkdAbGgDifg75mgHTUwBaAhHQHJOt+gDifh1fZQoaAZHQFNJEcKgIyFoB03oA2gIR0ByU8YO2AoYdX2UKGgGR0BxKxp8F6iTaAdNtwFoCEdAclbjBl+VknV9lChoBkdAcWjP2PDHfmgHTToBaAhHQHJX5nctXgd1fZQoaAZHQHJ3A22oegdoB00/AWgIR0ByWOfkFOfvdX2UKGgGR0BtMOSlnAZbaAdNJQFoCEdAclupsGgSOHV9lChoBkdAcJISgXdj5WgHTWQBaAhHQHJcsmOU+s51fZQoaAZHQGuxmapgkTpoB01dAWgIR0ByXccJdB0IdX2UKGgGR0BwOX5ylvZRaAdNNgFoCEdAcmCEtNBWxXV9lChoBkdAb/Y8PFvQ4WgHTVMBaAhHQHJhlObiIcl1fZQoaAZHQG/7xEF4cFRoB00nAWgIR0ByYnF2mpEQdX2UKGgGR0BsrA7HQyAQaAdNQAFoCEdAcmVAOavzOHV9lChoBkdAcGNawljVhGgHTQQBaAhHQHJmDhtLteF1fZQoaAZHQGy4DesPrfNoB00+AWgIR0ByZwcABDG+dX2UKGgGR0BxbxJGvwEyaAdNRwFoCEdAcmgJXQtz0nV9lChoBkdAcUo3oLXtjWgHTU0BaAhHQHJq/su3+dd1fZQoaAZHQHFplcpsoDxoB01UAWgIR0BybAuUUwi8dX2UKGgGR0ByM4dYGMXKaAdNQgFoCEdAcm0Rm9QGfXV9lChoBkdAcGoeenQ6ZGgHTQQBaAhHQHJvobn5i3J1fZQoaAZHQHBuQQHzH0doB01BAWgIR0BycKeoUBXCdX2UKGgGR0BxY+DkELYxaAdNJwFoCEdAcnGXu3MINXV9lChoBkdAcj7/Yao/A2gHTVABaAhHQHJ0SfYjB2x1fZQoaAZHQHBf3fyf+S9oB01hAWgIR0BydVle4TbndX2UKGgGR0BwsB4jbBXTaAdNUgFoCEdAcnZYJVsDXHV9lChoBkdAa3CiNbTts2gHTSgBaAhHQHJ5AXdj5Kx1fZQoaAZHQG8vnHWBjF1oB005AWgIR0ByefTOPeYVdX2UKGgGR0BytYqtozvaaAdNVAFoCEdAcnr/Lkjop3V9lChoBkdAb7Xf51vETGgHTUQBaAhHQHJ9+EM9bHJ1fZQoaAZHQG769cB2fTVoB01XAWgIR0Byfx0xM36zdX2UKGgGR0BvcHAoG6f8aAdNUwFoCEdAcoC3EAHVw3V9lChoBkdAcBlFcIJJG2gHTYUBaAhHQHKDo9kjHGV1fZQoaAZHQHAklnRLK3doB00lAWgIR0ByhIOG0u14dX2UKGgGR0BlHAvHtF8YaAdN6ANoCEdAcolwsXizcHV9lChoBkdAbZu1AJLM92gHTTcBaAhHQHKKWKAJ9iN1fZQoaAZHQHJHytmtheBoB019AWgIR0ByjV8b70nPdX2UKGgGR8A1KLA57w8XaAdLxmgIR0Byjff8/D+BdX2UKGgGR0Buj4GQjlgdaAdNRQFoCEdAco7wJgLJCHV9lChoBkdAcjzU9IPK+2gHTWIBaAhHQHKQBGlQ/HJ1fZQoaAZHQG+0a7dznzRoB01JAWgIR0BykqqHXVbzdX2UKGgGR0BwfCTMaCL/aAdNNgFoCEdAcpOZWq94/3V9lChoBkdAb/4U5dWyT2gHTRoBaAhHQHKUbUkOZst1fZQoaAZHQGF+hSLqD9RoB03oA2gIR0BymXPu5SWJdX2UKGgGR0BscExwhnrZaAdNYQFoCEdAcpxuaF23a3V9lChoBkdAcM88XN1QqWgHTYUBaAhHQHKdjvuw5eZ1fZQoaAZHQHGXuKKpDNRoB00bAWgIR0BynmVE/jbSdX2UKGgGR0BuXiq0dBBzaAdNIQFoCEdAcqEIcBEKE3V9lChoBkdAcuMqZML4OGgHTRoBaAhHQHKh2Mju8bt1fZQoaAZHQHAYhZMcp9ZoB00vAWgIR0Byor752yLRdX2UKGgGR0BME9UCJXQuaAdNDwFoCEdAcqOZ9uxbCHV9lChoBkdAb2l5VOsT4GgHTcUDaAhHQHKoZSNwR5F1fZQoaAZHQHB8mjCYTkBoB01EAWgIR0Byqwh4dIXkdX2UKGgGR0BxLc0rK/21aAdNOwFoCEdAcqvx9oexOnV9lChoBkdAbRpQO4G2TmgHTTUBaAhHQHKs4AGSpzd1fZQoaAZHQFBH8PnSv1VoB0vzaAhHQHKtlvl2eQN1fZQoaAZHQHCg32ugYgtoB01DAWgIR0BysIN2C/XYdX2UKGgGR0Bxmxjurp7kaAdNSQFoCEdAcrGBshxHXnV9lChoBkdAcLScWj4592gHTTkBaAhHQHKyeOGTLW91fZQoaAZHQHBnvvKEFntoB00rAWgIR0BytUXWOIZZdX2UKGgGR0BCR8cENe+maAdL+WgIR0Bytgis4ku6dX2UKGgGR0BxSoSVW0Z4aAdNLgFoCEdAcrbw482aUnVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3908, "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": 1, "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": "macOS-14.0-arm64-arm-64bit Darwin Kernel Version 23.0.0: Fri Sep 15 14:41:43 PDT 2023; root:xnu-10002.1.13~1/RELEASE_ARM64_T6000", "Python": "3.10.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.1", "GPU Enabled": "False", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}
|
ppo-lunar-lander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e1e8038be9cd92338d6c04754f4c464937682a6d0deb27468c8696491b49da1
|
3 |
+
size 146949
|
ppo-lunar-lander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
ppo-lunar-lander-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 0x1237bcaf0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x1237bcb80>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x1237bcc10>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x1237bcca0>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x1237bcd30>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x1237bcdc0>",
|
13 |
+
"extract_features": "<function ActorCriticPolicy.extract_features at 0x1237bce50>",
|
14 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x1237bcee0>",
|
15 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x1237bcf70>",
|
16 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x1237bd000>",
|
17 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x1237bd090>",
|
18 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x1237bd120>",
|
19 |
+
"__abstractmethods__": "frozenset()",
|
20 |
+
"_abc_impl": "<_abc._abc_data object at 0x1237b3200>"
|
21 |
+
},
|
22 |
+
"verbose": 1,
|
23 |
+
"policy_kwargs": {},
|
24 |
+
"num_timesteps": 1000448,
|
25 |
+
"_total_timesteps": 1000000,
|
26 |
+
"_num_timesteps_at_start": 0,
|
27 |
+
"seed": null,
|
28 |
+
"action_noise": null,
|
29 |
+
"start_time": 1701356632154613000,
|
30 |
+
"learning_rate": 0.0003,
|
31 |
+
"tensorboard_log": null,
|
32 |
+
"_last_obs": {
|
33 |
+
":type:": "<class 'numpy.ndarray'>",
|
34 |
+
":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGY3TT5umLA9umdavk2xs71XRBC9xaV7PQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
|
35 |
+
},
|
36 |
+
"_last_episode_starts": {
|
37 |
+
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
39 |
+
},
|
40 |
+
"_last_original_obs": null,
|
41 |
+
"_episode_num": 0,
|
42 |
+
"use_sde": false,
|
43 |
+
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": -0.00044800000000000395,
|
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": 3908,
|
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": 1,
|
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-lunar-lander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c90838d7200d64131b3e29c5f90dbbebf97f21630f34082416f6714f9f1c6b13
|
3 |
+
size 87978
|
ppo-lunar-lander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d3a8eea5c2211b21eacc025f4b579db3d156900f92cfde6240b24a232a33242
|
3 |
+
size 43634
|
ppo-lunar-lander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebdad4b9cfe9cd22a3abadb5623bf7bb1f6eb2e408740245eb3f2044b0adc018
|
3 |
+
size 864
|
ppo-lunar-lander-v2/system_info.txt
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: macOS-14.0-arm64-arm-64bit Darwin Kernel Version 23.0.0: Fri Sep 15 14:41:43 PDT 2023; root:xnu-10002.1.13~1/RELEASE_ARM64_T6000
|
2 |
+
- Python: 3.10.13
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.1.1
|
5 |
+
- GPU Enabled: False
|
6 |
+
- Numpy: 1.26.2
|
7 |
+
- Cloudpickle: 3.0.0
|
8 |
+
- Gymnasium: 0.28.1
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 256.37592137052945, "std_reward": 20.322270964907815, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-30T23:10:59.760603"}
|