Persistent Rule-based Interactive Reinforcement Learning

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

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
research
10/11/2022

Broad-persistent Advice for Interactive Reinforcement Learning Scenarios

The use of interactive advice in reinforcement learning scenarios allows...
research
08/21/2018

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

Given a text description, most existing semantic parsers synthesize a pr...
research
10/15/2021

A Broad-persistent Advising Approach for Deep Interactive Reinforcement Learning in Robotic Environments

Deep Reinforcement Learning (DeepRL) methods have been widely used in ro...
research
09/21/2020

Human Engagement Providing Evaluative and Informative Advice for Interactive Reinforcement Learning

Reinforcement learning is an approach used by intelligent agents to auto...
research
10/02/2019

Boosting Image Recognition with Non-differentiable Constraints

In this paper, we study the problem of image recognition with non-differ...
research
03/20/2021

RLTIR: Activity-based Interactive Person Identification based on Reinforcement Learning Tree

Identity recognition plays an important role in ensuring security in our...
research
06/24/2011

An Architectural Approach to Ensuring Consistency in Hierarchical Execution

Hierarchical task decomposition is a method used in many agent systems t...

Please sign up or login with your details

Forgot password? Click here to reset