arXiv research

New algorithm improves game learning with randomised optimism.

This paper tackles learning Stackelberg equilibrium in asymmetric games efficiently from noisy samples.

New algorithms improve on bandit feedback in matrix games with unknown payoff matrices.

The paper tackles Nash-regret minimization in congestion games with bandit feedback.

Efficiently identifies best algorithms for game tasks.

Research adapts Multi-Armed Bandits for Minesweeper, improving player strategy.

Improves bandit convex optimization with gradient variations.

New algorithms converge faster to Nash equilibrium in zero-sum games with bandit feedback.

Algorithm identifies best arm in combinatorial bandits with semi-bandit feedback.

A study on how a principal can incentivize an agent to make better decisions in a repeated game.

Two non-communicating players minimize regret in a multi-armed bandit game.

A new multi-armed bandit framework with credal sets for uncertain outcomes.

New algorithm reduces regret in graphical bilinear bandits.

New algorithm reduces risk in online games with limited feedback.

Algorithm learns NE in imperfect information games with imperfect feedback.

First sample-efficient algorithm for learning EFCE in bandit feedback settings.

Algorithm identifies correct hypothesis from alternatives in bandit problems.

MAXMINLCB optimizes unknown target functions with preference feedback using a Stackelberg game approach.

We obtain the conditions for the emergence of the swarm intelligence effect in an interactive game of restless multi-armed bandit (rMAB). A player competes with multiple agents. Each bandit has a payoff that changes with a probability $p_{c}$ per round. The agents and player choose one of three options: (1) Exploit (a …

Study of repeated games with unobserved agent rewards using MAB framework.

Paper solves learning imperfect-information games with fewer episodes.

Optimistic Thompson Sampling reduces regret in unknown multi-player games.

We consider the problem of learning to play a repeated multi-agent game with an unknown reward function. Single player online learning algorithms attain strong regret bounds when provided with full information feedback, which unfortunately is unavailable in many real-world scenarios. Bandit feedback alone, i.e., observ…

We study an original problem of pure exploration in a strategic bandit model motivated by Monte Carlo Tree Search. It consists in identifying the best action in a game, when the player may sample random outcomes of sequentially chosen pairs of actions. We propose two strategies for the fixed-confidence setting: Maximin…

We address the online linear optimization problem when the actions of the forecaster are represented by binary vectors. Our goal is to understand the magnitude of the minimax regret for the worst possible set of actions. We study the problem under three different assumptions for the feedback: full information, and the …

We study the problem of identifying the top $m$ arms in a multi-armed bandit game. Our proposed solution relies on a new algorithm based on successive rejects of the seemingly bad arms, and successive accepts of the good ones. This algorithmic contribution allows to tackle other multiple identifications settings that w…

We provide a simple and efficient algorithm for adversarial $k$-action $d$-outcome non-degenerate locally observable partial monitoring game for which the $n$-round minimax regret is bounded by $6(d+1) k^{3/2} \sqrt{n \log(k)}$, matching the best known information-theoretic upper bound. The same algorithm also achieves…

Study tests feasibility of linear programs with bandit feedback.

Paper develops efficient algorithms for learning rationalizable equilibria in multiplayer games.

Study of repeated principal-agent bandit game with self-interested and exploratory learning agents.

We introduce CSE for MLSF games and devise online learning algorithms for achieving no-external Stackelberg-regret.

IDS optimizes regret in stochastic partial monitoring with linear rewards.

Partial monitoring is a generalization of the well-known multi-armed bandit framework where the loss is not directly observed by the learner. We complete the classification of finite adversarial partial monitoring to include all games, solving an open problem posed by Bartok et al. [2014]. Along the way we simplify and…

Deep Reinforcement Learning has been shown to be very successful in complex games, e.g. Atari or Go. These games have clearly defined rules, and hence allow simulation. In many practical applications, however, interactions with the environment are costly and a good simulator of the environment is not available. Further…

Paper finds algorithms with both low regret and high exploitation.

Algorithm identifies the best arm in linear bandits with high probability.

New algorithm reduces individual regret and communication costs in cooperative bandits.

Pure exploration (aka active testing) is the fundamental task of sequentially gathering information to answer a query about a stochastic environment. Good algorithms make few mistakes and take few samples. Lower bounds (for multi-armed bandit models with arms in an exponential family) reveal that the sample complexity …

IDS algorithm optimizes sequential decisions in various monitoring settings.

The paper extends physics-based information maximization to complex bandit problems.

New bandit algorithm maximizes information gain.

Multi-armed bandits a simple but very powerful framework for algorithms that make decisions over time under uncertainty. An enormous body of work has accumulated over the years, covered in several books and surveys. This book provides a more introductory, textbook-like treatment of the subject. Each chapter tackles a p…

We study how to adapt to smoothly-varying ('easy') environments in well-known online learning problems where acquiring information is expensive. For the problem of label efficient prediction, which is a budgeted version of prediction with expert advice, we present an online algorithm whose regret depends optimally on t…

Bayesian methods suffer from the problem of how to specify prior beliefs. One interesting idea is to consider worst-case priors. This requires solving a stochastic zero-sum game. In this paper, we extend well-known results from bandit theory in order to discover minimax-Bayes policies and discuss when they are practica…

A new algorithm balances exploration and exploitation in online decision-making.

Algorithm identifies Pareto front in multi-objective bandits efficiently.

Mutation improves FTRL convergence in zero-sum games.

Saddle-point optimization problems are an important class of optimization problems with applications to game theory, multi-agent reinforcement learning and machine learning. A majority of the rich literature available for saddle-point optimization has focused on the offline setting. In this paper, we study nonstationar…