連続状態・行動・時間における価値反復法
Value Iteration in Continuous Actions, States and Time
既知のダイナミクスモデルを用い、連続状態・行動・時間で動的計画法を可能にするcFVIを提案。非線形制御実験で深層強化学習と同等の性能を示し、実機移行時の頑健性に優れることを示した。
著者: Michael Lutter, Shie Mannor, Jan Peters, Dieter Fox, Animesh Garg
分類: cs.LG, cs.RO, cs.SY, eess.SY
原文アブストラクト
Classical value iteration approaches are not applicable to environments with continuous states and actions. For such environments, the states and actions are usually discretized, which leads to an exponential increase in computational complexity. In this paper, we propose continuous fitted value iteration (cFVI). This algorithm enables dynamic programming for continuous states and actions with a known dynamics model. Leveraging the continuous-time formulation, the optimal policy can be derived for non-linear control-affine dynamics. This closed-form solution enables the efficient extension of value iteration to continuous environments. We show in non-linear control experiments that the dynamic programming solution obtains the same quantitative performance as deep reinforcement learning methods in simulation but excels when transferred to the physical system. The policy obtained by cFVI is more robust to changes in the dynamics despite using only a deterministic model and without explicitly incorporating robustness in the optimization. Videos of the physical system are available at \url{https://sites.google.com/view/value-iteration}.
