Picture for Hosein Hasanbeig

Hosein Hasanbeig

Progressive Safeguards for Safe and Model-Agnostic Reinforcement Learning

Add code
Oct 31, 2024
Viaarxiv icon

Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis

Add code
Dec 18, 2023
Figure 1 for Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis
Figure 2 for Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis
Figure 3 for Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis
Figure 4 for Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis
Viaarxiv icon

Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specifications

Add code
Nov 28, 2023
Figure 1 for Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specifications
Figure 2 for Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specifications
Figure 3 for Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specifications
Viaarxiv icon

In-Context Learning in Large Language Models: A Neuroscience-inspired Analysis of Representations

Add code
Oct 18, 2023
Viaarxiv icon

ALLURE: Auditing and Improving LLM-based Evaluation of Text using Iterative In-Context-Learning

Add code
Sep 27, 2023
Viaarxiv icon

Evaluating Cognitive Maps and Planning in Large Language Models with CogEval

Add code
Sep 25, 2023
Figure 1 for Evaluating Cognitive Maps and Planning in Large Language Models with CogEval
Figure 2 for Evaluating Cognitive Maps and Planning in Large Language Models with CogEval
Figure 3 for Evaluating Cognitive Maps and Planning in Large Language Models with CogEval
Figure 4 for Evaluating Cognitive Maps and Planning in Large Language Models with CogEval
Viaarxiv icon

LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learning

Add code
Sep 21, 2022
Viaarxiv icon