pith. sign in

arxiv: 1907.11788 · v1 · pith:7PZSRZD2new · submitted 2019-07-26 · 💻 cs.LG · cs.AI· stat.ML

On Hard Exploration for Reinforcement Learning: a Case Study in Pommerman

classification 💻 cs.LG cs.AIstat.ML
keywords explorationlearningpommermandomainmodel-freemodulerandomreinforcement
0
0 comments X
read the original abstract

How to best explore in domains with sparse, delayed, and deceptive rewards is an important open problem for reinforcement learning (RL). This paper considers one such domain, the recently-proposed multi-agent benchmark of Pommerman. This domain is very challenging for RL --- past work has shown that model-free RL algorithms fail to achieve significant learning without artificially reducing the environment's complexity. In this paper, we illuminate reasons behind this failure by providing a thorough analysis on the hardness of random exploration in Pommerman. While model-free random exploration is typically futile, we develop a model-based automatic reasoning module that can be used for safer exploration by pruning actions that will surely lead the agent to death. We empirically demonstrate that this module can significantly improve learning.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.