Abstraction for Deep Reinforcement Learning

2022-02-10 · Murray Shanahan, Melanie Mitchell

We characterise the problem of abstraction in the context of deep reinforcement learning. Various well established approaches to analogical reasoning and associative memory might be brought to bear on this issue, but they present difficulties because of the need for end-to-end differentiability. We review developments in AI and machine learning that could facilitate their adoption.

📄 PDF Abstract BibTeX arXiv:2202.05839

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningDeep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

State Abstractions for Lifelong Reinforcement Learning

2018-07-01 · ICML 2018 7 · David Abel, Dilip Arumugam, Lucas Lehnert, Michael Littman

In lifelong reinforcement learning, agents must effectively transfer knowledge across tasks while simultaneously addressing exploration, credit assignment, and generalization. State abstraction can help overcome the…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Contrastive Abstraction for Reinforcement Learning

2024-10-01 · Vihang Patil, Markus Hofmarcher, Elisabeth Rumetshofer, Sepp Hochreiter

Learning agents with reinforcement learning is difficult when dealing with long trajectories that involve a large number of states. To address these learning problems effectively, the number of states can be reduced by a…

Contrastive Learning Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

A Theory of Abstraction in Reinforcement Learning

2022-03-01 · David Abel

Reinforcement learning defines the problem facing agents that learn to make good decisions through action and observation alone. To be effective problem solvers, such agents must efficiently explore vast worlds, assign c…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Answer-Set-Programming-based Abstractions for Reinforcement Learning

2026-05-29 · Rafael Bankosegger, Thomas Eiter, Johannes Oetsch arxiv

Reinforcement Learning (RL) enables autonomous agents to learn policies from experience, but realistic problems often involve enormous state spaces, making learning and generalisation challenging. Abstraction and approxi…

Reinforcement Learning

Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning

2026-06-24 · Yivan Zhang, Ziyan Luo, Manuel Baltieri arxiv

State abstraction plays a key role in scaling reinforcement learning to complex but structured systems. In studying such systems, a wide range of behavioral structures have been studied in reinforcement learning, includi…