activity
20242026
collaborators
Showing stat.MLShow all

5 papers · 1 filter

stat.ML2026

Proximal Point Nash Learning from Human Feedback

Daniil Tiapkin, Daniele Calandriello, Denis Belomestny +5

Traditional Reinforcement Learning from Human Feedback (RLHF) often relies on reward models, frequently assuming preference structures like the Bradley--Terry model, which may not…

stat.ML2025

Model-free Posterior Sampling via Learning Rate Randomization

Daniil Tiapkin, Denis Belomestny, Daniele Calandriello +6

In this paper, we introduce Randomized Q-learning (RandQL), a novel randomized model-free algorithm for regret minimization in episodic Markov Decision Processes (MDPs). To the bes…

stat.ML2025

Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games

Antonio Ocello, Daniil Tiapkin, Lorenzo Mancini +2

We introduce Mean-Field Trust Region Policy Optimization (MF-TRPO), a novel algorithm designed to compute approximate Nash equilibria for ergodic Mean-Field Games (MFG) in finite s…

stat.ML2024

Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential Stability

Sergey Samsonov, Daniil Tiapkin, Alexey Naumov +1

In this paper we consider the problem of obtaining sharp bounds for the performance of temporal difference (TD) methods with linear function approximation for policy evaluation in…

stat.ML2024

Demonstration-Regularized RL

Daniil Tiapkin, Denis Belomestny, Daniele Calandriello +5

Incorporating expert demonstrations has empirically helped to improve the sample efficiency of reinforcement learning (RL). This paper quantifies theoretically to what extent this…