ビデオゲームから実機ロボットへ：行動空間の転移
From Video Game to Real Robot: The Transfer between Action Spaces
一般的なビデオゲームをシミュレーションの代わりに使い、ゲームとロボットで行動空間が異なる場合でもニューラルネットの一部再学習で新行動空間を自律獲得し、実機で90%超の成功率を達成した。
著者: Janne Karttunen, Anssi Kanervisto, Ville Kyrki, Ville Hautamäki
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Deep reinforcement learning has proven to be successful for learning tasks in simulated environments, but applying same techniques for robots in real-world domain is more challenging, as they require hours of training. To address this, transfer learning can be used to train the policy first in a simulated environment and then transfer it to physical agent. As the simulation never matches reality perfectly, the physics, visuals and action spaces by necessity differ between these environments to some degree. In this work, we study how general video games can be directly used instead of fine-tuned simulations for the sim-to-real transfer. Especially, we study how the agent can learn the new action space autonomously, when the game actions do not match the robot actions. Our results show that the different action space can be learned by re-training only part of neural network and we obtain above 90% mean success rate in simulation and robot experiments.
