Picture for Marcello Restelli

Marcello Restelli

A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning

Add code
Jun 21, 2024
Viaarxiv icon

The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough

Add code
Jun 18, 2024
Figure 1 for The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough
Figure 2 for The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough
Figure 3 for The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough
Figure 4 for The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough
Viaarxiv icon

Interpetable Target-Feature Aggregation for Multi-Task Learning based on Bias-Variance Analysis

Add code
Jun 12, 2024
Viaarxiv icon

Optimal Multi-Fidelity Best-Arm Identification

Add code
Jun 05, 2024
Viaarxiv icon

How to Explore with Belief: State Entropy Maximization in POMDPs

Add code
Jun 04, 2024
Viaarxiv icon

Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs

Add code
May 10, 2024
Viaarxiv icon

Policy Gradient with Active Importance Sampling

Add code
May 09, 2024
Viaarxiv icon

Information Capacity Regret Bounds for Bandits with Mediator Feedback

Add code
Feb 15, 2024
Viaarxiv icon

Sharing Knowledge in Multi-Task Deep Reinforcement Learning

Add code
Jan 17, 2024
Viaarxiv icon

Inverse Reinforcement Learning with Sub-optimal Experts

Add code
Jan 08, 2024
Viaarxiv icon