Articles by Mohammad Gheshlaghi Azar | Synthical

Synthical

Your space

Profile

Activity

Favorites

Folders

Feeds

Contacts

About

Claim page

Mohammad Gheshlaghi Azar

Follow

Activity

Upvotes

Folders

Articles

25

Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion

16 January 2025 by Yannis Flet-Berliac and others

Machine Learning

Averaging log-likelihoods in direct alignment

27 June 2024 by Nathan Grinsztajn and others

Machine Learning

Nash Learning from Human Feedback

11 June 2024 by Rémi Munos and others at

Inria Rocquencourt

Machine Learning, Artificial Intelligence

Self-Improving Robust Preference Optimization

1

7 June 2024 by Eugene Choi and others

Machine Learning, Artificial Intelligence

Offline Regularised Reinforcement Learning for Large Language Models Alignment

29 May 2024 by Pierre Harvey Richemond and others at

Machine Learning, Artificial Intelligence

An Analysis of Quantile Temporal-Difference Learning

20 May 2024 by Mark Rowland and others

Machine Learning

A General Theoretical Paradigm to Understand Learning from Human Preferences

1

22 November 2023 by Mohammad Gheshlaghi Azar and others at

Artificial Intelligence, Machine Learning

Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice

22 May 2023 by Toshinori Kitamura and others

Machine Learning

Understanding Self-Predictive Learning for Reinforcement Learning

6 December 2022 by Yunhao Tang and others

Machine Learning, Artificial Intelligence

BYOL-Explore: Exploration by Bootstrapped Prediction

16 June 2022 by Zhaohan Daniel Guo and others

Machine Learning, Artificial Intelligence

KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal

27 May 2022 by Tadashi Kozuno and others

Machine Learning, Artificial Intelligence

Large-Scale Representation Learning on Graphs via Bootstrapping

4 November 2021 by Shantanu Thakoor and others

Machine Learning, Social and Information Networks

Bootstrap your own latent: A new approach to self-supervised Learning

9 September 2020 by Jean-Bastien Grill and others

Machine Learning, Computer Vision and Pattern Recognition

The Advantage Regret-Matching Actor-Critic

27 August 2020 by Audrūnas Gruslys and others

Artificial Intelligence, Machine Learning

Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

30 April 2020 by Daniel Guo and others

Machine Learning, Artificial Intelligence

Neural Predictive Belief Representations

19 August 2019 by Zhaohan Daniel Guo and others

Machine Learning

World Discovery Models

21 February 2019 by Mohammad Gheshlaghi Azar and others

Artificial Intelligence, Applications

The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning

19 June 2018 by Audrunas Gruslys and others

Artificial Intelligence

Observe and Look Further: Achieving Consistent Performance on Atari

29 May 2018 by Tobias Pohlen and others

Machine Learning, Artificial Intelligence

Noisy Networks for Exploration

15 February 2018 by Meire Fortunato and others

Machine Learning

Minimax Regret Bounds for Reinforcement Learning

1 July 2017 by Mohammad Gheshlaghi Azar and others

Machine Learning, Artificial Intelligence

Convex Relaxation Regression: Black-Box Optimization of Smooth Functions by Learning Their Convex Envelopes

16 February 2016 by Mohammad Gheshlaghi Azar and others

Machine Learning

Stochastic Optimization of a Locally Smooth Function under Correlated Bandit Feedback

13 February 2014 by Mohammad Gheshlaghi Azar and others

Machine Learning, Systems and Control

Sequential Transfer in Multi-armed Bandit with Finite Set of Models

25 July 2013 by Mohammad Gheshlaghi Azar and others

Machine Learning

Regret Bounds for Reinforcement Learning with Policy Advice

17 July 2013 by Mohammad Gheshlaghi Azar and others

Machine Learning

On the Sample Complexity of Reinforcement Learning with a Generative Model

27 June 2012 by Mohammad Gheshlaghi Azar and others at

Inria Rocquencourt

Machine Learning

Dynamic Policy Programming

6 September 2011 by Mohammad Gheshlaghi Azar and others

Machine Learning, Artificial Intelligence

This is an AI-generated summary

Key points

Topics

Machine Learning Artificial Intelligence Systems and Control Computer Science and Game Theory Multiagent Systems Social and Information Networks Computer Vision and Pattern Recognition Applications Optimization and Control