スパース報酬に強い多目的モデルベース方策探索
Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards
学習したダイナミクスモデルを用いて新規性・報酬・モデル精度の3目的をパレート最適化し、スパース報酬タスクを少ない試行で解く手法Multi-DEXを提案。
著者: Rituraj Kaushik, Konstantinos Chatzilygeroudis, Jean-Baptiste Mouret
分類: cs.LG, cs.AI, cs.NE, cs.RO, stat.ML
原文アブストラクト
The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. However, the current algorithms lack an effective exploration strategy to deal with sparse or misleading reward scenarios: if they do not experience any state with a positive reward during the initial random exploration, it is very unlikely to solve the problem. Here, we propose a novel model-based policy search algorithm, Multi-DEX, that leverages a learned dynamical model to efficiently explore the task space and solve tasks with sparse rewards in a few episodes. To achieve this, we frame the policy search problem as a multi-objective, model-based policy optimization problem with three objectives: (1) generate maximally novel state trajectories, (2) maximize the expected return and (3) keep the system in state-space regions for which the model is as accurate as possible. We then optimize these objectives using a Pareto-based multi-objective optimization algorithm. The experiments show that Multi-DEX is able to solve sparse reward scenarios (with a simulated robotic arm) in much lower interaction time than VIME, TRPO, GEP-PG, CMA-ES and Black-DROPS.
関連論文
- 潜在想像によるパラメータ化行動空間の学習モデルベースRL
- チャンク単位のモデルベース方策最適化モデルベースRL
- モデルベース強化学習における動力学変化下でのリプレイ保持の特性評価モデルベースRL
- モデルベース強化学習のための償却低ランク適応モデルベースRL
- 変化点対応ワールドモデル:動力学シフトの検出と古いリプレイの忘却による回復モデルベースRL
- RENEW: 選好から世界モデルの学習とモデル悪用の修復を目指してモデルベースRL
