fw9wef Goto Github PK

bipedalwalker

detectorgan

gpt2_summ

gpt-2 based summarization model trained with reinforcement learining

hse_rl_course

nle

The NetHack Learning Environment

patched_ecole

Nodesel dynamics for Extensible Combinatorial Optimization Learning Environments

pgn_bleurt

practical_rl

A course in reinforcement learning in the wild

pytorch-lifestream

A library built upon PyTorch for building embeddings on discrete event sequences using self-supervision

retro_branching

Learning to branch with reinforcement learning using retrospective trajectories for exact combinatorial optimisation.

rl2branch

self_critic_gpt2

speech_denoising

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

trl

Train transformer language models with reinforcement learning.

zapret

DPI bypass multi platform