Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning

2022-05-28 · Remo Sasso, Matthia Sabatelli, Marco A. Wiering

A crucial challenge in reinforcement learning is to reduce the number of interactions with the environment that an agent requires to master a given task. Transfer learning proposes to address this issue by re-using knowledge from previously learned tasks. However, determining which source task qualifies as the most appropriate for knowledge extraction, as well as the choice regarding which algorithm components to transfer, represent severe obstacles to its application in reinforcement learning. The goal of this paper is to address these issues with modular multi-source transfer learning techniques. The proposed techniques automatically learn how to extract useful information from source tasks, regardless of the difference in state-action space and reward function. We support our claims with extensive and challenging cross-domain experiments for visual control.

📄 PDF Abstract BibTeX arXiv:2205.14410

Code (0)

등록된 구현이 없습니다.

Tasks

Continuous ControlModel-based Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Transfer Learning

Meta-RTL: Reinforcement-Based Meta-Transfer Learning for Low-Resource Commonsense Reasoning

2024-09-27 · Yu Fu, Jie He, Yifan Yang, Qun Liu 외

Meta learning has been widely used to exploit rich-resource source tasks to improve the performance of low-resource target tasks. Unfortunately, most existing meta learning approaches treat different source tasks equally…

Meta-Learning Transfer Learning

Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning

2025-05-24 · Chi Zhang, Ziying Jia, George K. Atia, Sihong He 외

Transfer reinforcement learning aims to derive a near-optimal policy for a target environment with limited data by leveraging abundant data from related source domains. However, it faces two key challenges: the lack of p…

reinforcement-learning Reinforcement Learning Transfer Learning Transfer Reinforcement Learning

Transfer from Multiple MDPs

2011-12-01 · NeurIPS 2011 12 · Alessandro Lazaric, Marcello Restelli

Transfer reinforcement learning (RL) methods leverage on the experience collected on a set of source tasks to speed-up RL algorithms. A simple and effective approach is to transfer samples from source tasks and include t…

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

Cross-Domain Transfer in Reinforcement Learning using Target Apprentice

2018-01-22 · Girish Joshi, Girish Chowdhary

In this paper, we present a new approach to Transfer Learning (TL) in Reinforcement Learning (RL) for cross-domain tasks. Many of the available techniques approach the transfer architecture as a method of speeding up the…

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

MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics

2019-09-28 · Mohammadamin Barekatain, Ryo Yonetani, Masashi Hamaya

Transfer reinforcement learning (RL) aims at improving the learning efficiency of an agent by exploiting knowledge from other source agents trained on relevant tasks. However, it remains challenging to transfer knowledge…

Reinforcement Learning Reinforcement Learning (RL)Transfer Reinforcement Learning