Article

Learning Safe Behaviour via Justified Human Preferences and Hypothetical Queries

2022-12-29

Abstract excerpt

<title>Abstract</title> <p>Although reinforcement learning is a powerful paradigm for agent sequential decision-making, it cannot be used in its traditional form in most safety-critical environments. Human feedback can enable an agent to learn a good policy while avoiding unsafe states, but at the cost of human time. We present JPAL-HA, a model for safe learning in safety-critical environments that is grounded on...

Topics

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

Identifiers and source

Literature Corpus work: 0f3305e2-2baf-5eed-a3cb-ec516323a750
DOI: 10.21203/rs.3.rs-2406802/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Learning Safe Behaviour via Justified Human Preferences and Hypothetical QueriesDOI 10.21203/rs.3.rs-2406802/v1Read

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

On the computational principles underlying human explorationSemantic proximity Read

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

EXPLAINABLE REINFORCEMENT LEARNING FOR TRANSPARENT AUTONOMOUS DECISION SYSTEMSSemantic proximity Read

Cognitive Escape Reinforcement Learning for Complex Decision MakingSemantic proximity Read

The Value of AbstractionSemantic proximity Read

CAUSAL EXPLAINABLE REINFORCEMENT LEARNING FOR RELIABLE AUTONOMOUS DECISION-MAKING IN DYNAMIC ENVIRONMENTSSemantic proximity Read

Toward Zero-Human-Intervention Autonomous Robot Learning: A Continuous Result-Driven Self-Reward and Correction FrameworkSemantic proximity Read

Learning from Explanations With Maximum Likelihood Inverse Reinforcement LearningSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read