Picture for Kamil Ciosek

Kamil Ciosek

University College London

Observation Noise and Initialization in Wide Neural Networks

Add code
Feb 03, 2025
Viaarxiv icon

Impatient Bandits: Optimizing for the Long-Term Without Delay

Add code
Jan 14, 2025
Viaarxiv icon

Epistemic Uncertainty and Observation Noise with the Neural Tangent Kernel

Add code
Sep 10, 2024
Figure 1 for Epistemic Uncertainty and Observation Noise with the Neural Tangent Kernel
Viaarxiv icon

On the Importance of Uncertainty in Decision-Making with Large Language Models

Add code
Apr 03, 2024
Viaarxiv icon

Automatic Music Playlist Generation via Simulation-based Reinforcement Learning

Add code
Oct 13, 2023
Figure 1 for Automatic Music Playlist Generation via Simulation-based Reinforcement Learning
Figure 2 for Automatic Music Playlist Generation via Simulation-based Reinforcement Learning
Figure 3 for Automatic Music Playlist Generation via Simulation-based Reinforcement Learning
Figure 4 for Automatic Music Playlist Generation via Simulation-based Reinforcement Learning
Viaarxiv icon

Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay

Add code
Jul 20, 2023
Viaarxiv icon

A Strong Baseline for Batch Imitation Learning

Add code
Feb 06, 2023
Figure 1 for A Strong Baseline for Batch Imitation Learning
Figure 2 for A Strong Baseline for Batch Imitation Learning
Figure 3 for A Strong Baseline for Batch Imitation Learning
Figure 4 for A Strong Baseline for Batch Imitation Learning
Viaarxiv icon

Imitation Learning by Reinforcement Learning

Add code
Aug 10, 2021
Figure 1 for Imitation Learning by Reinforcement Learning
Viaarxiv icon

Information Directed Reward Learning for Reinforcement Learning

Add code
Feb 24, 2021
Figure 1 for Information Directed Reward Learning for Reinforcement Learning
Figure 2 for Information Directed Reward Learning for Reinforcement Learning
Figure 3 for Information Directed Reward Learning for Reinforcement Learning
Figure 4 for Information Directed Reward Learning for Reinforcement Learning
Viaarxiv icon

Estimating $α$-Rank by Maximizing Information Gain

Add code
Jan 22, 2021
Figure 1 for Estimating $α$-Rank by Maximizing Information Gain
Figure 2 for Estimating $α$-Rank by Maximizing Information Gain
Figure 3 for Estimating $α$-Rank by Maximizing Information Gain
Figure 4 for Estimating $α$-Rank by Maximizing Information Gain
Viaarxiv icon