Dale Schuurmans

Learning to Reason Efficiently with Discounted Reinforcement Learning

The Effect of Temporal Resolution in Offline Temporal Difference Estimation

Judging with Confidence: Calibrating Autoraters to Preference Distributions

Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback

The World Is Bigger: A Computationally-Embedded Perspective on the Big World Hypothesis

REINFORCE Converges to Optimal Policies with Any Learning Rate

Toward Understanding In-context vs. In-weight Learning

Learning Continually by Spectral Regularization

Plastic Learning with Deep Fourier Features

Soft Preference Optimization: Aligning Language Models to Expert Distributions

Improving Large Language Model Planning with Action Sequence Similarity

Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Exploring and Benchmarking Planning Capabilities of Large Language Models