activity
20242026
collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

Utility-Constrained Policy Optimization

Mehrdad Moghimi, Bernardo Avila Pires

Constrained MDPs (CMDPs) are a widely adopted framework for incorporating safety into RL agents; however, the framework does not support risk-sensitive constraints. This can be pro…

cs.LG2025

Optimizing Return Distributions with Distributional Dynamic Programming

Bernardo Ávila Pires, Mark Rowland, Diana Borsa +6

We introduce distributional dynamic programming (DP) methods for optimizing statistical functionals of the return distribution, with standard reinforcement learning as a special ca…

cs.LG2025

Representation Learning via Non-Contrastive Mutual Information

Zhaohan Daniel Guo, Bernardo Avila Pires, Khimya Khetarpal +2

Labeling data is often very time consuming and expensive, leaving us with a majority of unlabeled data. Self-supervised representation learning methods such as SimCLR (Chen et al.,…

cs.LG2024

A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning

Khimya Khetarpal, Zhaohan Daniel Guo, Bernardo Avila Pires +7

Learning a good representation is a crucial challenge for Reinforcement Learning (RL) agents. Self-predictive learning provides means to jointly learn a latent representation and d…

cs.LG2024

Offline Regularised Reinforcement Learning for Large Language Models Alignment

Pierre Harvey Richemond, Yunhao Tang, Daniel Guo +15

The dominant framework for alignment of large language models (LLM), whether through reinforcement learning from human feedback or direct preference optimisation, is to learn from…

cs.LG2024

Generalized Preference Optimization: A Unified Approach to Offline Alignment

Yunhao Tang, Zhaohan Daniel Guo, Zeyu Zheng +7

Offline preference optimization allows fine-tuning large models directly from offline data, and has proved effective in recent alignment practices. We propose generalized preferenc…