# Efficient Deep Reinforcement Learning via Adaptive Policy Transfer

arXiv: https://arxiv.org/abs/2002.08037 · HTML: https://mlsanity.com/paper/2002.08037/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2020.

## Built on by (most cited first, 4 of 4)

- [CUP: Critic-Guided Policy Reuse](https://mlsanity.com/paper/2210.08153/) (2022)
- [SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration](https://mlsanity.com/paper/2211.13743/) (2022)
- [On the Value of Myopic Behavior in Policy Reuse](https://mlsanity.com/paper/2305.17623/) (2023)
- [Using Cooperative Game Theory to Prune Neural Networks](https://mlsanity.com/paper/2311.10468/) (2023)

## Abstract (arXiv)

Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing transfer approaches either explicitly computes the similarity between tasks or select appropriate source policies to provide guided explorations for the target task. However, how to directly optimize the target policy by alternatively utilizing knowledge from appropriate source policies without explicitly measuring the similarity is currently missing. In this paper, we propose a novel Policy Transfer Framework (PTF) to accelerate RL by taking advantage of this idea. Our framework learns when and which source policy is the best to reuse for the target policy and when to terminate it by modeling multi-policy transfer as the option learning problem. PTF can be easily combined with existing deep RL approaches. Experimental results show it significantly accelerates the learning process and surpasses state-of-the-art policy transfer methods in terms of learning efficiency and final performance in both discrete and continuous action spaces.