Options Of Interest: Temporal Abstraction With Interest Functions

Abstract

Temporal abstraction refers to the ability of an agent to use behaviours of controllers which act for a limited, variable amount of time. The options framework describes such behaviours as consisting of a subset of states in which they can initiate, an internal policy and a stochastic termination condition. However, much of the subsequent work on option discovery has ignored the initiation set, because of difficulty in learning it from data. We provide a generalization of initiation sets suitable for general function approximation, by defining an interest function associated with an option. We derive a gradient-based learning algorithm for interest functions, leading to a new interest-option-critic architecture. We investigate how interest functions can be leveraged to learn interpretable and reusable temporal abstractions. We demonstrate the efficacy of the proposed approach through quantitative and qualitative results, in both discrete and continuous environments.

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keykhetarpal2020options

Related papers

• Attention Option-critic (2022)0.00
• Multi-timescale, Gradient Descent, Temporal Difference Learning With Linear Options (2017)0.00
• Autonomous Option Invention For Continual Hierarchical Reinforcement Learning And Planning (2024)2.26
• Option-critic In Cooperative Multi-agent Systems (2019)0.00
• Reusable Options Through Gradient-based Meta Learning (2022)0.00
• The Termination Critic (2019)0.00
• A Hierarchical Reinforcement Learning Method For Persistent Time-sensitive Tasks (2016)0.00
• Learning When To Act: Interval-aware Reinforcement Learning With Predictive Temporal Structure (2026)0.00