Article

Learning from Explanations With Maximum Likelihood Inverse Reinforcement Learning

2022-03-21

Abstract excerpt

<title>Abstract</title> <p>Our research effort takes inspiration from human social learning mechanisms to focus on situations in which an expert guides a learner through explanations. The proposed approach incorporates explanations into maximum likelihood inverse reinforcement learning. We computationally evaluate explanations against other teaching signals (reward, demonstration and explanation) in three navigat...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 71589586-99ee-5f6e-a30a-41280ac56a64
DOI: 10.21203/rs.3.rs-1439366/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Learning from Explanations With Maximum Likelihood Inverse Reinforcement LearningDOI 10.21203/rs.3.rs-1439366/v1Read

A Policy-Graph Approach to Explain Reinforcement Learning Agents: A Novel Policy-Graph Approach with Natural Language and Counterfactual Abstractions for Explaining Reinforcement Learning AgentsSemantic proximity Read

Modeling sensory-motor decisions in natural behaviorSemantic proximity Read

Learning from other minds: An optimistic critique of reinforcement learning models of social learningSemantic proximity Read

Learning Safe Behaviour via Justified Human Preferences and Hypothetical QueriesSemantic proximity Read

How Much to Explain? Personalised Explainability for a Delivery Robot that Adapts the Level of DetailSemantic proximity Read

Learning Safe Behaviour via Justified Human Preferences and Hypothetical QueriesSemantic proximity Read

Multi-Task Reinforcement Learning in HumansSemantic proximity Read

EXPLAINABLE REINFORCEMENT LEARNING FOR TRANSPARENT AUTONOMOUS DECISION SYSTEMSSemantic proximity Read

Explaining the Behaviour of Reinforcement Learning Agents in a Multi-Agent Cooperative Environment Using Policy GraphsSemantic proximity Read

Cognitive Escape Reinforcement Learning for Complex Decision MakingSemantic proximity Read

On the computational principles underlying human explorationSemantic proximity Read

BayesCog: A freely available course in Bayesian statistics and hierarchical Bayesian modeling for psychological scienceSemantic proximity Read