Knowledge Transfer In Multi-task Deep Reinforcement Learning For Continuous Control
2020 · Zhiyuan Xu, Kun Wu, Zhengping Che, et al.
Abstract
While Deep Reinforcement Learning (DRL) has emerged as a promising approach to many complex tasks, it remains challenging to train a single DRL agent that is capable of undertaking multiple different continuous control tasks. In this paper, we present a Knowledge Transfer based Multi-task Deep Reinforcement Learning framework (KTM-DRL) for continuous control, which enables a single DRL agent to achieve expert-level performance in multiple different tasks by learning from task-specific teachers. In KTM-DRL, the multi-task agent first leverages an offline knowledge transfer algorithm designed particularly for the actor-critic architecture to quickly learn a control policy from the experience of task-specific teachers, and then it employs an online learning algorithm to further improve itself by learning from new online transition samples under the guidance of those teachers. We perform a comprehensive empirical study with two commonly-used benchmarks in the MuJoCo continuous control task
Authors
(none)
Tags
Stats
Related papers
- Multi-granularity Knowledge Transfer For Continual Reinforcement Learning (2024)2.26
- Ensemble Reinforcement Learning In Continuous Spaces -- A Hierarchical Multi-step Approach For Policy Training (2022)2.26
- Learning Robust And Adaptive Real-world Continuous Control Using Simulation And Transfer Learning (2018)0.00
- A Model-based Approach For Sample-efficient Multi-task Reinforcement Learning (2019)0.00
- Exploring Reinforcement Learning Techniques For Discrete And Continuous Control Tasks In The Mujoco Environment (2023)0.00
- Sa-matd3:self-attention-based Multi-agent Continuous Control Method In Cooperative Environments (2021)11.76
- Continual Policy Distillation From Distributed Reinforcement Learning Teachers (2026)0.00
- Attraction-repulsion Actor-critic For Continuous Control Reinforcement Learning (2019)0.00