少数の専門家デモで効率的に誘導する深層強化学習
Exploration-efficient Deep Reinforcement Learning with Demonstration Guidance for Robot Control
SACをベースに、少数の専門家デモから識別器とガイダーを学習し、適切な状態でエージェントを誘導することで探索効率と学習安定性を改善した手法を提案。
著者: Ke Lin, Liang Gong, Xudong Li, Te Sun, Binhao Chen, Chengliang Liu, Zhengfeng Zhang, Jian Pu, Junping Zhang
分類: cs.RO
原文アブストラクト
Although deep reinforcement learning (DRL) algorithms have made important achievements in many control tasks, they still suffer from the problems of sample inefficiency and unstable training process, which are usually caused by sparse rewards. Recently, some reinforcement learning from demonstration (RLfD) methods have shown to be promising in overcoming these problems. However, they usually require considerable demonstrations. In order to tackle these challenges, on the basis of the SAC algorithm we propose a sample efficient DRL-EG (DRL with efficient guidance) algorithm, in which a discriminator D(s) and a guider G(s) are modeled by a small number of expert demonstrations. The discriminator will determine the appropriate guidance states and the guider will guide agents to better exploration in the training phase. Empirical evaluation results from several continuous control tasks verify the effectiveness and performance improvements of our method over other RL and RLfD counterparts. Experiments results also show that DRL-EG can help the agent to escape from a local optimum.
