Ensemble Reinforcement Learning In Continuous Spaces -- A Hierarchical Multi-step Approach For Policy Training

Abstract

Actor-critic deep reinforcement learning (DRL) algorithms have recently achieved prominent success in tackling various challenging reinforcement learning (RL) problems, particularly complex control tasks with high-dimensional continuous state and action spaces. Nevertheless, existing research showed that actor-critic DRL algorithms often failed to explore their learning environments effectively, resulting in limited learning stability and performance. To address this limitation, several ensemble DRL algorithms have been proposed lately to boost exploration and stabilize the learning process. However, most of existing ensemble algorithms do not explicitly train all base learners towards jointly optimizing the performance of the ensemble. In this paper, we propose a new technique to train an ensemble of base learners based on an innovative multi-step integration method. This training technique enables us to develop a new hierarchical learning algorithm for ensemble DRL that effectively p

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keychen2022ensemble

Related papers

• Broad Critic Deep Actor Reinforcement Learning For Continuous Control (2024)0.00
• Deep Multi-agent Reinforcement Learning With Discrete-continuous Hybrid Action Spaces (2019)12.47
• Efficient Exploration In Deep Reinforcement Learning: A Novel Bayesian Actor-critic Algorithm (2024)0.00
• Multi-agent Actor-critic For Mixed Cooperative-competitive Environments (2017)0.00
• Centralized Cooperative Exploration Policy For Continuous Control Tasks (2023)0.00
• A Further Exploration Of Deep Multi-agent Reinforcement Learning With Hybrid Action Space (2022)5.84
• A New Framework For Multi-agent Reinforcement Learning -- Centralized Training And Exploration With Decentralized Execution Via Policy Distillation (2019)0.00
• Deep Exploration With Pac-bayes (2024)0.00