Persistent Rule-based Interactive Reinforcement Learning

02/04/2021 ∙ by Adam Bignold, et al. ∙ 0 ∙ share

Interactive reinforcement learning has allowed speeding up the learning process in autonomous agents by including a human trainer providing extra information to the agent in real-time. Current interactive reinforcement learning research has been limited to interactions that offer relevant advice to the current state only. Additionally, the information provided by each interaction is not retained and instead discarded by the agent after a single-use. In this work, we propose a persistent rule-based interactive reinforcement learning approach, i.e., a method for retaining and reusing provided knowledge, allowing trainers to give general advice relevant to more than just the current state. Our experimental results show persistent advice substantially improves the performance of the agent while reducing the number of interactions required for the trainer. Moreover, rule-based advice shows similar performance impact as state-based advice, but with a substantially reduced interaction count.

READ FULL TEXT

Persistent Rule-based Interactive Reinforcement Learning

Authors

Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning

Human Engagement Providing Evaluative and Informative Advice for Interactive Reinforcement Learning

Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving

Boosting Image Recognition with Non-differentiable Constraints

A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Review

Learning how to learn: an adaptive dialogue agent for incrementally learning visually grounded word meanings

A Framework for Integrating Gesture Generation Models into Interactive Conversational Agents

Persistent Rule-based Interactive Reinforcement Learning

Authors

Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning

Human Engagement Providing Evaluative and Informative Advice for Interactive Reinforcement Learning

Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving

Boosting Image Recognition with Non-differentiable Constraints

A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Review

Learning how to learn: an adaptive dialogue agent for incrementally learning visually grounded word meanings

A Framework for Integrating Gesture Generation Models into Interactive Conversational Agents

This week in AI