情報理論で強化する身体性エージェントの強化学習
Information Theoretically Aided Reinforcement Learning for Embodied Agents
連続するセンサ読み取り間の相互情報量を内在的報酬として加えることで、複雑な形態の移動学習における方策勾配最適化を改善する手法を実験的に示した。
著者: Guido Montufar, Keyan Ghazi-Zahedi, Nihat Ay
分類: cs.AI, cs.RO, math.OC, stat.ML
原文アブストラクト
Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental setting, that incorporating an intrinsic reward can smoothen the optimization landscape while preserving the global optimizers of interest. We show that policy gradient optimization for locomotion in a complex morphology is significantly improved when supplementing the extrinsic reward by an intrinsic reward defined in terms of the mutual information of time consecutive sensor readings.
