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

2018-06-25 · Rituraj Kaushik, Konstantinos Chatzilygeroudis, Jean-Baptiste Mouret

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.

📄 PDF Abstract BibTeX arXiv:1806.09351

Code (1)

resibots/kaushik_2018_multi-dex 공식 구현

Tasks

Continuous ControlEfficient ExplorationReinforcement Learning

Methods 이 논문이 사용한 방법론

TRPO Trust Region Policy Optimization, or TRPO, is a policy gradient method in reinforcement learning that avoids parameter updates that change the policy too much with a KL…

AT$^2$PO: Agentic Turn-based Policy Optimization via Tree Search

2026-01-08 · Zefang Zong, Dingwei Chen, Yang Li, Qi Yi 외 arxiv

LLM agents have emerged as powerful systems for tackling multi-turn tasks by interleaving internal reasoning and external tool interactions. Agentic Reinforcement Learning has recently drawn significant research attentio…

Reinforcement Learning

Occupancy Information Ratio: Infinite-Horizon, Information-Directed, Parameterized Policy Search

2022-01-21 · Wesley A. Suttle, Alec Koppel, Ji Liu

In this work, we propose an information-directed objective for infinite-horizon reinforcement learning (RL), called the occupancy information ratio (OIR), inspired by the information ratio objectives used in previous inf…

Multi-Armed Bandits Reinforcement Learning (RL)

PRISM: Parallel Reward Integration with Symmetry for MORL

2026-02-20 · Finn van der Knaap, Kejiang Qian, Zheng Xu, Fengxiang He arxiv

This work studies heterogeneous Multi-Objective Reinforcement Learning (MORL), where objectives can differ sharply in temporal frequency. Such heterogeneity allows dense objectives to dominate learning, while sparse long…

Reinforcement Learning

Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction

2024-04-09 · Jinyuan Feng, Min Chen, Zhiqiang Pu, Tenghai Qiu 외

Multi-task reinforcement learning (MTRL) demonstrate potential for enhancing the generalization of a robot, enabling it to perform multiple tasks concurrently. However, the performance of MTRL may still be susceptible to…

reinforcement-learning Reinforcement Learning

Generalizing Across Multi-Objective Reward Functions in Deep Reinforcement Learning

2018-09-17 · Eli Friedman, Fred Fontaine

Many reinforcement-learning researchers treat the reward function as a part of the environment, meaning that the agent can only know the reward of a state if it encounters that state in a trial run. However, we argue tha…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)