No project description provided
Project description
Torch Lure
Depndencies
pip install git+https://github.com/Farama-Foundation/Minari.git@19565bd8cd33f2e4a3a9a8e4db372044b01ea8d3
pip install torchlure
Usage
import torchlure as lure
# Optimizers
lure.SophiaG(lr=1e-3, weight_decay=0.2)
# Functions
lure.tanh_exp(x)
lure.TanhExp()
lure.quantile_loss(y_pred, y_target, quantile=0.5)
lure.QuantileLoss(quantile=0.5)
lure.RMSNrom(dim=256, eps=1e-6)
# Noise Scheduler
lure.LinearNoiseScheduler(beta=1e-4, beta_end=0.02, num_timesteps=1000)
lure.CosineNoiseScheduler(max_beta=0.999, s=0.008, num_timesteps=1000):
Dataset
from torchlure.datasets import MinariEpisodeDataset, MinariTrajectoryDataset
env = gym.make("Hopper-V4")
minari_dataset = MinariEpisodeDataset("2048.2407.2")
minari_dataset.create(env, n_episodes=100)
minari_dataset.info()
traj_dataset = MinariTrajectoryDataset(minari_dataset, traj_len=20)
ep = traj_dataset[2]
ep["observations"].shape, ep["actions"].shape, ep["rewards"].shape, ep[
"terminations"
].shape, ep["truncate"].shape
ep = traj_dataset[[3, 8, 15]]
ep = traj_dataset[np.arange(16)]
ep = traj_dataset[torch.arange(16)]
ep = traj_dataset[-16:]
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
torchlure-0.2407.0.tar.gz
(18.6 kB
view hashes)
Built Distribution
Close
Hashes for torchlure-0.2407.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 217771a1114138720dbdefdc96780c528d963867916068fcd749142767a2706c |
|
MD5 | 78d0fdc17f6e2a0e2125e6a2c7d50bc2 |
|
BLAKE2b-256 | 7cb5cca4e9de9eff2036f6d1921cabe4555c8c198a3090c6015da40ee867905b |