Human-Allied Relational Reinforcement Learning
Preprint
Abstract
Reinforcement learning (RL) has experienced a second wind in the past decade. While incredibly successful in images and videos, these systems still operate within the realm of propositional tasks ignoring the inherent structure that exists in the problem. Consequently, relational extensions (RRL) have been developed for such structured problems that allow for effective generalization to arbitrary number of objects. However, they inherently make strong assumptions about the problem structure. We introduce a novel framework that combines RRL with object-centric representation to handle both structured and unstructured data. We enhance learning by allowing the system to actively query the human expert for guidance by explicitly modeling the uncertainty over the policy. Our empirical evaluation demonstrates the effectiveness and efficiency of our proposed approach.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- A Survey on Recent Advancements in Autonomous Driving Using Deep Reinforcement Learning: Applications, Challenges, and SolutionsIEEE Transactions on Intelligent Transportation Systems, 2024
- Human-in-the-Loop Reinforcement Learning: A Survey and Position on Requirements, Challenges, and OpportunitiesJournal of Artificial Intelligence Research, 2024
- Explainable Action Advising for Multi-Agent Reinforcement Learning2023
- Persistent rule-based interactive reinforcement learningNeural Computing and Applications, 2021
- Challenges of real-world reinforcement learning: definitions, benchmarks and analysisMachine Learning, 2021
- Guiding Autonomous Agents to Better Behaviors through Human Advice2013
- The Arcade Learning Environment: An Evaluation Platform for General AgentsJournal of Artificial Intelligence Research, 2013
- Probabilistic policy reuse in a reinforcement learning agent2006