プログレッシブネットによるピクセル入力からのsim-to-realロボット学習
Sim-to-Real Robot Learning from Pixels with Progressive Nets
プログレッシブネットワークを用いてシミュレーションで学習した方策を実機ロボットへ転移し、生の画像入力と疎な報酬のみでマニピュレーションタスクを実機学習できることを示した論文。
著者: Andrei A. Rusu, Mel Vecerik, Thomas Rothörl, Nicolas Heess, Razvan Pascanu, Raia Hadsell
分類: cs.RO, cs.LG
原文アブストラクト
Applying end-to-end learning to solve complex, interactive, pixel-driven control tasks on a robot is an unsolved problem. Deep Reinforcement Learning algorithms are too slow to achieve performance on a real robot, but their potential has been demonstrated in simulated environments. We propose using progressive networks to bridge the reality gap and transfer learned policies from simulation to the real world. The progressive net approach is a general framework that enables reuse of everything from low-level visual features to high-level policies for transfer to new tasks, enabling a compositional, yet simple, approach to building complex skills. We present an early demonstration of this approach with a number of experiments in the domain of robot manipulation that focus on bridging the reality gap. Unlike other proposed approaches, our real-world experiments demonstrate successful task learning from raw visual input on a fully actuated robot manipulator. Moreover, rather than relying on model-based trajectory optimisation, the task learning is accomplished using only deep reinforcement learning and sparse rewards.
