paper-with-me

홈 › Papers

A Geometric Perspective on Optimal Representations for Reinforcement Learning

2019-01-31 · NeurIPS 2019 12 · Marc G. Bellemare, Will Dabney, Robert Dadashi, Adrien Ali Taiga, Pablo Samuel Castro, Nicolas Le Roux, Dale Schuurmans, Tor Lattimore, Clare Lyle

We propose a new perspective on representation learning in reinforcement learning based on geometric properties of the space of value functions. We leverage this perspective to provide formal evidence regarding the usefulness of value functions as auxiliary tasks. Our formulation considers adapting the representation to minimize the (linear) approximation of the value function of all stationary policies for a given environment. We show that this optimization reduces to making accurate predictions regarding a special class of value functions which we call adversarial value functions (AVFs). We demonstrate that using value functions as auxiliary tasks corresponds to an expected-error relaxation of our formulation, with AVFs a natural candidate, and identify a close relationship with proto-value functions (Mahadevan, 2005). We highlight characteristics of AVFs and their usefulness as auxiliary tasks in a series of experiments on the four-room domain.

📄 PDF Abstract BibTeX arXiv:1901.11530

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Representation Learning

Similar Papers 제목 키워드 기반

Understanding Reward Ambiguity Through Optimal Transport Theory in Inverse Reinforcement Learning

2023-10-18 · Ali Baheri

In inverse reinforcement learning (IRL), the central objective is to infer underlying reward functions from observed expert behaviors in a way that not only explains the given data but also generalizes to unseen scenario…

reinforcement-learning

A Closed-Loop Multi-perspective Visual Servoing Approach with Reinforcement Learning

2023-12-25 · Lei Zhang, Jiacheng Pei, Kaixin Bai, Zhaopeng Chen 외

Traditional visual servoing methods suffer from serving between scenes from multiple perspectives, which humans can complete with visual signals alone. In this paper, we investigated how multi-perspective visual servoing…

OpenAI Gymreinforcement-learning

What Representational Similarity Measures Imply about Decodable Information

2024-11-12 · Sarah E. Harvey, David Lipshutz, Alex H. Williams

Neural responses encode information that is useful for a variety of downstream tasks. A common approach to understand these systems is to build regression models or ``decoders'' that reconstruct features of the stimulus …

On the Optimal Representation Efficiency of Barlow Twins: An Information-Geometric Interpretation

2025-10-13 · Di Zhang arxiv

Self-supervised learning (SSL) has achieved remarkable success by learning meaningful representations without labeled data. However, a unified theoretical framework for understanding and comparing the efficiency of diffe…

Self-Supervised Learning

Thinking with Spatial Code for Physical-World Video Reasoning

2026-03-05 · Jieneng Chen, Wenxin Ma, Ruisheng Yuan, Yunzhi Zhang 외 arxiv

We introduce Thinking with Spatial Code, a framework that transforms RGB video into explicit, temporally coherent 3D representations for physical-world visual question answering. We highlight the empirical finding that o…

Visual Question AnsweringReinforcement Learning