5 accepted papers
Model-based reinforcement learning (MBRL) hinges on a learned dynamics model whose errors can compound along imagined rollouts. We study how encouraging \emph{flatness} in the model’s training loss affects downstream control, and show that steering optimization toward flatter minima yields a better…
Agents that can build temporally abstract representations of their environment are better able to understand their world and make plans on extended time scales, with limited computational power and modeling capacity. However, existing methods for automatically learning temporally abstract world mode…
One of the preeminent obstacles to scaling multi-agent reinforcement learning to large numbers of agents is assigning credit to individual agents’ actions. In this letter, we address this credit assignment problem with an approach that we call <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" x
Decentralized multi-agent reinforcement learning has been demonstrated to be an effective solution to large multiagent control problems. However, agents typically can only make decisions based on local information, resulting in suboptimal performance in partially-observable settings. The addition of
Recent approaches to multi-agent reinforcement learning (MARL) with inter-agent communication have often overlooked important considerations of real-world communication networks, such as limits on bandwidth. In this paper, we propose an approach to learning sparse discrete communication through back…