Picture for Josiah P. Hanna

Josiah P. Hanna

Stable Offline Value Function Learning with Bisimulation-based Representations

Add code
Oct 02, 2024
Viaarxiv icon

Reinforcement Learning via Auxiliary Task Distillation

Add code
Jun 24, 2024
Viaarxiv icon

Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning

Add code
Jun 07, 2024
Viaarxiv icon

SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP

Add code
Jun 04, 2024
Viaarxiv icon

Adaptive Exploration for Data-Efficient General Value Function Evaluations

Add code
May 13, 2024
Viaarxiv icon

On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling

Add code
Nov 14, 2023
Viaarxiv icon

Multi-task Representation Learning for Pure Exploration in Bilinear Bandits

Add code
Nov 01, 2023
Viaarxiv icon

Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning

Add code
Oct 27, 2023
Viaarxiv icon

State-Action Similarity-Based Representations for Off-Policy Evaluation

Add code
Oct 27, 2023
Viaarxiv icon

Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates

Add code
Oct 26, 2023
Viaarxiv icon