Structural Similarity for Improved Transfer in Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
Transfer learning is an increasingly common approach for developing performant RL agents. However, it is not well understood how to define the relationship between the source and target tasks, and how this relationship contributes to successful transfer. We present an algorithm called Structural Similarity for Two MDPS, or SS2, that calculates a state similarity measure for states in two finite MDPs based on previously developed bisimulation metrics, and show that the measure satisfies properties of a distance metric. Then, through empirical results with GridWorld navigation tasks, we provide evidence that the distance measure can be used to improve transfer performance for Q-Learning agents over previous implementations.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 29 references that are in the map. First posted on arXiv 27 Jul 2022.
Builds on
10 of 29 references.
References · 10
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
- 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
- 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 436
- 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
- 2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 274
- 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 265
- 2019Scalable methods for computing state similarity in deterministic Markov Decision Processescited by 133
- 2021MICo: Improved representations via sampling-based state similarity for Markov decision processescited by 43
- 2021A Taxonomy of Similarity Metrics for Markov Decision Processescited by 6
- 2013Clustering Markov Decision Processes For Continual Transfercited by 4
Built on by
Not cited yet.