Eccles, T; Bachrach, Y; Lever, G; Lazaridou, A; Graepel, T; (2019) Biases for Emergent Communication in Multi-agent Reinforcement Learning. In: Wallach, HM and Larochelle, H and Beygelzimer, A and d'Alché-Buc, F and Fox, EA and Garnett, R, (eds.) Proceedings of Advances in Neural Information Processing Systems 32 (NIPS 2019). (pp. pp. 13111-13121). Neural Information Processing Systems Foundation, Inc.: Vancouver, Canada.

Preview

Text Biases for Emergent Communication in Multi-agent Reinforcement Learning.pdf - Published Version Download (589kB) | Preview

Abstract

We study the problem of emergent communication, in which language arises because speakers and listeners must communicate information in order to solve tasks. In temporally extended reinforcement learning domains, it has proved hard to learn such communication without centralized training of agents, due in part to a difficult joint exploration problem. We introduce inductive biases for positive signalling and positive listening, which ease this problem. In a simple one-step environment, we demonstrate how these biases ease the learning problem. We also apply our methods to a more extended environment, showing that agents with these inductive biases achieve better performance, and analyse the resulting communication protocols.

Download activity - last month

Export as JSONCSVXML

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item