方策蒸留とSim2Real転移による実環境での継続強化学習
Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer
3輪オムニロボットの2Dナビゲーションを題材に、状態表現学習と方策蒸留を組み合わせて、逐次与えられる複数タスクを忘れずに解く継続強化学習手法を実機へ適用した。
著者: René Traoré, Hugo Caselles-Dupré, Timothée Lesort, Te Sun, Natalia Díaz-Rodríguez, David Filliat
分類: cs.LG, cs.RO, stat.ML
原文アブストラクト
We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary work on applying Reinforcement Learning to such setting, on 2D navigation tasks for a 3 wheel omni-directional robot. Our approach takes advantage of state representation learning and policy distillation. Policies are trained using learned features as input, rather than raw observations, allowing better sample efficiency. Policy distillation is used to combine multiple policies into a single one that solves all encountered tasks.
