Safer Deep RL with Shallow MCTS: A Case Study in Pommerman

Safer Deep RL with Shallow MCTS: A Case Study in Pommerman

B. Kartal, P. Hernandez-Leal, C. Gao, and M. E. Taylor. International Conference on Autonomous Agents and Multiagent Systems Workshop on Adaptive and Learning Agents (AAMAS), 2019

Reinforcement Learning