bycn

bycn.github.io

bsuite

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

client

🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.

dm_control

The DM Control Suite and Package is a tool for developing and testing reinforcement learning agents for the MuJoCo physics engine.

gym

A toolkit for developing and comparing reinforcement learning algorithms.

gym-moving-dot

A simple moving dot environment for OpenAI Gym to test reinforcement learning algorithms

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

jps

Code for "Joint Policy Search for Collaborative Multi-agent Incomplete Information Games"

libmelee

Open Python 3 API for making your own Smash Bros: Melee AI that works with Slippi Online

midlevel-reps

Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies

oldjekyll

Build a Jekyll blog in minutes, without touching the command line.

pytorch_sac

PyTorch implementation of Soft Actor-Critic (SAC)

rlkit

Collection of reinforcement learning algorithms

rlpyt

Reinforcement Learning in PyTorch

sp18

DS100 Spring 2018 Course Repository

stable-baselines

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

uda_release

Unsupervised Domain Adaptation through Self-Supervision

visual-prior

Code for Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies. Arxiv preprint 2018. Alexander Sax, Bradley Emi, Amir R. Zamir, Silvio Savarese, Leonidas Guibas, Jitendra Malik.