brett-daley

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

arxiv-style

A Latex style and template for paper preprints (based on NIPS style)

envpool

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

purejaxrl

Really Fast End-to-End Jax RL Implementations

framework-reproducibility

Providing reproducibility in deep learning frameworks

SimpleParsing

Simple, Elegant, Typed Argument Parsing with argparse

MinAtar

mnist_png

MNIST converted to PNG format

dm_control2gym

OpenAI Gym Wrapper for DeepMind Control Suite

randomdict

Python dictionaries with O(1) random element access.

nmt-en-vi

Neural Machine Translation system for English to Vietnamese (IWSLT'15 English-Vietnamese data)

Reinforcement-Learning-Lunar_Lander

gym-gridverse

Gridworld domains in the gym interface

lstm

Training an LSTM network on the Penn Tree Bank (PTB) dataset

belief-grounded-network

[CoRL 2020] Belief-Grounded Networks for Accelerated Robot Learning under Partial Observability

atari-prediction-benchmark

nupar-bench

The NUPAR benchmark suite targets the modern GPU architectures.