Search Results for author:
Found 26 papers, 3 papers with code
Local and adaptive mirror descents in extensive-form games
We study how to learn $\epsilon$-optimal strategies in zero-sum imperfect information games (IIG) with trajectory feedback.
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Mirror descent value iteration (MDVI), an abstraction of Kullback-Leibler (KL) and entropy-regularized reinforcement learning (RL), has served as the basis for recent high-performing practical RL algorithms.
Learning Generative Models with Goal-conditioned Reinforcement Learning
We present a novel, alternative framework for learning generative models with goal-conditioned reinforcement learning.
Adapting to game trees in zero-sum imperfect information games
Imperfect information games (IIG) are games in which each player only partially observes the current game state.
KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal
In this work, we consider and analyze the sample complexity of model-free reinforcement learning with a generative model.
Indexed Minimum Empirical Divergence for Unimodal Bandits
We consider a multi-armed bandit problem specified by a set of one-dimensional family exponential distributions endowed with a unimodal structure.
Learning in two-player zero-sum partially observable Markov games with perfect recall
We study the problem of learning a Nash equilibrium (NE) in an extensive game with imperfect information (EGII) through self-play.
Adaptive Multi-Goal Exploration
We introduce a generic strategy for provably efficient multi-goal exploration.
Problem Dependent View on Structured Thresholding Bandit Problems
Taking $K$ as the number of arms, we consider the case where (i) the sequence of arm's means $(\mu_k)_{k=1}^K$ is monotonically increasing (MTBP) and (ii) the case where $(\mu_k)_{k=1}^K$ is concave (CTBP).
Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall
We study the problem of learning a Nash equilibrium (NE) in an imperfect information game (IIG) through self-play.
Bandits with many optimal arms
We characterize the optimal learning rates both in the cumulative regret setting, and in the best-arm identification setting in terms of the problem parameters $T$ (the budget), $p^*$ and $\Delta$.
Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited
In this paper, we propose new problem-independent lower bounds on the sample complexity and regret in episodic MDPs, with a particular focus on the non-stationary case in which the transition kernel is allowed to change in each stage of the episode.
Fast active learning for pure exploration in reinforcement learning
Realistic environments often provide agents with very limited feedback.
A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces
In this work, we propose KeRNS: an algorithm for episodic reinforcement learning in non-stationary Markov Decision Processes (MDPs) whose state-action set is endowed with a metric.
Optimal Strategies for Graph-Structured Bandits
[0, 1]^{\mathcal{A}\times\mathcal{B}}$ and by a given weight matrix $\omega\!=\!
Gamification of Pure Exploration for Linear Bandits
We investigate an active pure-exploration setting, that includes best-arm identification, in the context of linear stochastic bandits.
Adaptive Reward-Free Exploration
Reward-free exploration is a reinforcement learning setting studied by Jin et al. (2020), who address it by running several algorithms with regret guarantees in parallel.
Planning in Markov Decision Processes with Gap-Dependent Sample Complexity
We propose MDP-GapE, a new trajectory-based Monte-Carlo Tree Search algorithm for planning in a Markov Decision Process in which transitions have a finite support.
Kernel-Based Reinforcement Learning: A Finite-Time Analysis
We consider the exploration-exploitation dilemma in finite-horizon reinforcement learning problems whose state-action space is endowed with a metric.
Fixed-Confidence Guarantees for Bayesian Best-Arm Identification
We investigate and provide new insights on the sampling rule called Top-Two Thompson Sampling (TTTS).
Non-Asymptotic Pure Exploration by Solving Games
Pure exploration (aka active testing) is the fundamental task of sequentially gathering information to answer a query about a stochastic environment.
Gradient Ascent for Active Exploration in Bandit Problems
We present a new algorithm based on an gradient ascent for a general Active Exploration bandit problem in the fixed confidence setting.
Thresholding Bandit for Dose-ranging: The Impact of Monotonicity
We analyze the sample complexity of the thresholding bandit problem, with and without the assumption that the mean values of the arms are increasing.
A minimax and asymptotically optimal algorithm for stochastic bandits
We propose the kl-UCB ++ algorithm for regret minimization in stochastic bandit models with exponential families of distributions.
Explore First, Exploit Next: The True Shape of Regret in Bandit Problems
We revisit lower bounds on the regret in the case of multi-armed bandit problems.
