Title

DCRAC: Deep Conditioned Recurrent Actor-Critic for Multi-Objective Partially Observable Environments

Publication Date

5-2020

Document Type

Article

Abstract

In many decision-making problems, agents aim to balance multiple, possibly conflicting objectives. Existing research in deep reinforcement learning mainly focuses on fully-observable single-objective solutions. In this paper, we propose DCRAC, a deep reinforcement learning framework for solving partially-objective multi-objective problems. DCRAC follows a conditioned actor-critic approach in learning the optimal policy, where the network is conditioned on the weights, i.e, relative importance for the different objectives. To deal with longer action-observation histories, in the case of partially observable environments, we introduce DCRAC-M which uses memory networks to further enhance the reasoning ability of the agent. Experimental evaluation on benchmark problems show the superiority of our approach when compared to state-of-the-art.

Publication Title

Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems

Publisher Policy

No SHERPA/RoMEO policy available

Open Access Status

Licensed

This document is currently not available here.

Find in your library

Share

COinS