The Adaptive Stress Testing for Robust AI (ASTRA) toolbox provides tooling to support model developers and testing in the full life cycle of making more robust AI Systems through the application of…

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

A benchmark environment for fully cooperative human-AI performance.

Google Research

A curated list of publically available human-robot interaction datasets

Jupyter notebook containing a solution to Sutton and Barto's gridworld problem with both a random agent and a Q-learning agent.

Adversarial attacks in consensus-based multi-agent reinforcement learning

Gridworld for MARL experiments

RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code

gym minigrid for multi-agent

Extension of `gym-minigrid` to handle multi-agent pushing

Train agents on MiniGrid from human demonstrations using Inverse Reinforcement Learning