Generative Integration Networks

•

Shohei Ohsawa
25 Sep 2019 (modified: 24 Dec 2019)ICLR 2020 Conference Desk Rejected SubmissionReaders: EveryoneShow Bibtex
Keywords: Synchrony, State Representations, Generative RNNs, Adversarial Learning, Multi-agent Communication
Abstract: This paper presents an unbiased exploration framework for the belief state in non-cooperative, multi-agent, partially-observable environments through differentiable recurrent functions. As well as single-agent exploration via intrinsic reward and generative RNNs, several researchers have proposed differentiable multi-agent communication models such as CommNet and IC3Net for scalable exploration through multiple agents. However, none of the existing frameworks so far capture the unbiased belief state in non-cooperative settings as with the nature due to biased examples reported from adersarial agents. {\em Generative integration networks} (GINs) is the first unbiased exploration framework insipired by honest reporting mechanisms in economics. The key idea is {\em synchrony}, an inter-agent reward to discriminate the honest reporting and the adversarial reporting \textbf{without real examples}, which is the different point from the GANs. Experimental results obtained using two non-cooperative multi-agent environments up to 20 agents denote that GINs show state-of-the-art performance in the exploration frameworks.
Original Pdf:  pdf
1 Reply
Add
Show
from
[–]

Submission Desk Rejected by Program Chairs

•

ICLR 2020 Conference Program Chairs
20 Oct 2019ICLR 2020 Conference Paper1924 Desk RejectReaders: Everyone
Desk Reject Comments: This paper violates the dual submission policy, with substantial overlap between this paper and one submitted to another conference in parallel.
Add