Steven Ho

madrl-baselines. Some multiagent deep reinforcement learning algorithms and its PyTorch implementation.

VALOR. Implementation of VALOR (Variational Option Discovery Algorithms)

coma. Multi-agent algorithm based on counterfactual multi-agent policy gradients

diayn-sac. DIYAN implementation based on SAC (PyTorch Ver.)

ingress_rawdata_process. public tool for processing ingress rawdata retrieved from Niantics.

multiagent-particle-envs. forked from https://github.com/openai/multiagent-particle-envs, altered to own usage.

gym-navigation. A simple environment based on gym. Only 2D continuous navigation by far.

diayn-cont. Extension of DIAYN w/ continuous latent space.

dads-exp. Python