Optimal Options For Multi-task Reinforcement Learning Under Time Constraints

Abstract

Reinforcement learning can greatly benefit from the use of options as a way of encoding recurring behaviours and to foster exploration. An important open problem is how can an agent autonomously learn useful options when solving particular distributions of related tasks. We investigate some of the conditions that influence optimality of options, in settings where agents have a limited time budget for learning each task and the task distribution might involve problems with different levels of similarity. We directly search for optimal option sets and show that the discovered options significantly differ depending on factors such as the available learning time budget and that the found options outperform popular option-generation heuristics.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydelverme2020optimal

Related papers

• A Hierarchical Reinforcement Learning Method For Persistent Time-sensitive Tasks (2016)0.00
• Reusable Options Through Gradient-based Meta Learning (2022)0.00
• An Autonomous Non-monolithic Agent With Multi-mode Exploration Based On Options Framework (2023)0.00
• A Model-based Approach For Sample-efficient Multi-task Reinforcement Learning (2019)0.00
• Exploring With Sticky Mittens: Reinforcement Learning With Expert Interventions Via Option Templates (2022)0.00
• Individual Specialization In Multi-task Environments With Multiagent Reinforcement Learners (2019)0.00
• Multi-agent Deep Covering Skill Discovery (2022)0.00
• Time Limits In Reinforcement Learning (2017)0.00