Minqi

learning-to-communicate-pytorch. Learning to Communicate with Deep Multi-Agent Reinforcement Learning in PyTorch

hnatt. Train and visualize Hierarchical Attention Networks

wordcraft. An environment for benchmarking commonsense agents

alphazero. Generic implementation of AlphaZero

PyMDP. Markov decision processes in Python

procgen. Procgen Benchmark: Procedurally Generated Game-Like Gym Environments