A Deep Policy Inference Q-Network for Multi-Agent Systems
This work addresses a specific challenge in multi-agent reinforcement learning for controllable agents interacting with collaborators and opponents, offering incremental improvements over existing methods.
The paper tackles the problem of modeling agents with varying strategies in multi-agent systems by proposing DPIQN and DRPIQN, which use policy features to improve Q-value predictions, resulting in superior performance over baseline models in soccer game scenarios with concrete gains in stability and mean scores.
We present DPIQN, a deep policy inference Q-network that targets multi-agent systems composed of controllable agents, collaborators, and opponents that interact with each other. We focus on one challenging issue in such systems---modeling agents with varying strategies---and propose to employ "policy features" learned from raw observations (e.g., raw images) of collaborators and opponents by inferring their policies. DPIQN incorporates the learned policy features as a hidden vector into its own deep Q-network (DQN), such that it is able to predict better Q values for the controllable agents than the state-of-the-art deep reinforcement learning models. We further propose an enhanced version of DPIQN, called deep recurrent policy inference Q-network (DRPIQN), for handling partial observability. Both DPIQN and DRPIQN are trained by an adaptive training procedure, which adjusts the network's attention to learn the policy features and its own Q-values at different phases of the training process. We present a comprehensive analysis of DPIQN and DRPIQN, and highlight their effectiveness and generalizability in various multi-agent settings. Our models are evaluated in a classic soccer game involving both competitive and collaborative scenarios. Experimental results performed on 1 vs. 1 and 2 vs. 2 games show that DPIQN and DRPIQN demonstrate superior performance to the baseline DQN and deep recurrent Q-network (DRQN) models. We also explore scenarios in which collaborators or opponents dynamically change their policies, and show that DPIQN and DRPIQN do lead to better overall performance in terms of stability and mean scores.