日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

模倣学習arXiv:1806.01267

観測の内部モデルによる報酬整形

Internal Model from Observations for Reward Shaping

シェア:XThreadsFacebookLINEはてブBluesky

専門家の状態軌跡から観測の内部予測モデルを学習し、実状態と予測状態の差を報酬として強化学習を行う手法を提案。マリオやFlappy Birdで専門家のプレイ動画から良好な方策を学習できることを示した。

著者: Daiki Kimura, Subhajit Chaudhury, Ryuki Tachibana, Sakyasingha Dasgupta

分類: cs.LG, cs.AI, cs.RO, stat.ML

原文アブストラクト

Reinforcement learning methods require careful design involving a reward function to obtain the desired action policy for a given task. In the absence of hand-crafted reward functions, prior work on the topic has proposed several methods for reward estimation by using expert state trajectories and action pairs. However, there are cases where complete or good action information cannot be obtained from expert demonstrations. We propose a novel reinforcement learning method in which the agent learns an internal model of observation on the basis of expert-demonstrated state trajectories to estimate rewards without completely learning the dynamics of the external environment from state-action pairs. The internal model is obtained in the form of a predictive model for the given expert state distribution. During reinforcement learning, the agent predicts the reward as a function of the difference between the actual state and the state predicted by the internal model. We conducted multiple experiments in environments of varying complexity, including the Super Mario Bros and Flappy Bird games. We show our method successfully trains good policies directly from expert game-play videos.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI