Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards - Archive ouverte HAL Access content directly
Conference Papers Year :

Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards

(1) , (1) , (1)
1

Abstract

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 cumulative reward 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.
Fichier principal
Vignette du fichier
mops (1).pdf (1.13 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01884294 , version 1 (30-09-2018)

Identifiers

Cite

Rituraj Kaushik, Konstantinos Chatzilygeroudis, Jean-Baptiste Mouret. Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards. CoRL 2018 - Conference on Robot Learning, Oct 2018, Zurich, Switzerland. ⟨hal-01884294⟩
73 View
99 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More