Adding action masking to pufferlib

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

⏰ AI conference deadline countdowns

Example Streamlit app that you can fork to test out share.streamlit.io

A data-driven, fast driving simulator for multi-agent coordination under partial observability.

pip install antialiased-cnns to improve stability and accuracy

NVIDIA's Deep Imagination Team's PyTorch Library

A fast and differentiable model predictive control (MPC) solver for PyTorch.

DrQ-v2: Improved Data-Augmented Reinforcement Learning

Waymo Open Dataset

This is the official implementation of Multi-Agent PPO (MAPPO).

Robotics Gym Environments

[RSS 2019] End-to-End Robotic Reinforcement Learning without Reward Engineering

Learning Latent Dynamics for Planning from Pixels

A high-performance distributed execution engine

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

[ICRA19] Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning

Code repository for Active Domain Randomization (https://arxiv.org/abs/1904.04762)

Git Source Code Mirror - This is a publish-only repository and all pull requests are ignored. Please follow Documentation/SubmittingPatches procedure for any of your improvements.

Visual MPC implementation running on Rethink Sawyer Robot

A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents!

Web-based 3D visualization of SUMO microsimulations using TraCI and three.js.