Multi-objective path integral policy improvement for learning robotic motion
Authors:
Open Access
- 2 May 2025
- journal article
- research article
- Published by Springer Nature in Artificial Life and Robotics
- p. 1-12
Abstract
This paper proposes a new multi-objective reinforcement learning (MORL) algorithm for robotics by extending policy improvement with path integral ( $$\text {PI}^2$$ ) algorithm. For a robot motion acquisition problem, most existing MORL algorithms are hard to apply, because of the high-dimensional and continuous state and action spaces. However, policy-based algorithms such as $$\text {PI}^2$$ can be applied to solve this problem in single-objective cases. Based on the similarity of $$\text {PI}^2$$ and evolution strategies (ESs) and the fact that ESs are well-suited for multi-objective optimization, we propose an extension of $$\text {PI}^2$$ and some techniques to speed up the learning. The effectiveness is shown via numerical simulations.
Keywords
This publication has 16 references indexed in Scilit:
- Automatic Temperature Parameter Tuning for Reinforcement Learning Using Path Integral Policy ImprovementIEEE Transactions on Neural Networks and Learning Systems, 2023
- Efficient Elitist Cooperative Evolutionary Algorithm for Multi-Objective Reinforcement LearningIEEE Access, 2023
- Actor-critic multi-objective reinforcement learning for non-linear utility functionsAutonomous Agents and Multi-Agent Systems, 2023
- Interaction-Based Prediction for Dynamic Multiobjective OptimizationIEEE Transactions on Evolutionary Computation, 2023
- Multi-objective fuzzy Q-learning to solve continuous state-action problemsNeurocomputing, 2022
- A multiobjective evolutionary algorithm based on decision variable classification for many-objective optimizationSwarm and Evolutionary Computation, 2022
- Path Integral Policy Improvement With Population AdaptationIEEE Transactions on Cybernetics, 2020
- Policy search in continuous action domains: An overviewNeural Networks, 2019
- A fast and elitist multiobjective genetic algorithm: NSGA-IIIEEE Transactions on Evolutionary Computation, 2002
- Multiobjective optimization using evolutionary algorithms — A comparative case study1998