Truthful Self-Play

Shohei Ohsawa

arXiv 6 Jun 2021 · Statistics — Machine Learning

arXiv:2106.03007 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We present a general framework for evolutionary learning to emergent unbiased state representation without any supervision. Evolutionary frameworks such as self-play converge to bad local optima in case of multi-agent reinforcement learning in non-cooperative partially observable environments with communication due to information asymmetry. Our proposed framework is a simple modification of self-play inspired by mechanism design, also known as {\em reverse game theory}, to elicit truthful signals and make the agents cooperative. The key idea is to add imaginary rewards using the peer prediction method, i.e., a mechanism for evaluating the validity of information exchanged between agents in a decentralized environment. Numerical experiments with predator prey, traffic junction and StarCraft tasks demonstrate that the state-of-the-art performance of our framework.

Citation extraction

appendix boundary found by appendix_command · 97% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

Showing the top 8 of 8 scored citations. 8 of these could not be matched to a bibliography entry, so only the citation key is shown.