ERMAS: Becoming Robust to Reward Function Sim-to-Real Gaps in Multi-Agent Simulations.

Eric Zhao Alexander R. Trott Caiming Xiong Stephan Zheng

Published in: CoRR (2021)

Keyphrases

multi agent
reward function
multiple agents
reinforcement learning
inverse reinforcement learning
markov decision processes
state space
agent based simulations
search algorithm