arXiv research

New approach to multi-armed bandit problem aims to maximize highest total reward.

Reward tweaking optimizes behavior for long-term goals by adjusting the reward function.

Reinforcement learning mimics expert behavior.

Unified theory for UCB policies in total and max bandit problems.

Optimizing rewards under budget constraints with correlated costs and rewards.

Contextual bandits are online learners that, given an input, select an arm and receive a reward for that arm. They use the reward as a learning signal and aim to maximize the total reward over the inputs. Contextual bandits are commonly used to solve recommendation or ranking problems. This paper considers a learning s…

Algorithm maximizes total reward in multi-agent bandits with adversarial corruptions.

New method reduces total cost constraints in CBwK to sqrt(T) with fairness application.

Adaptive KL-UCB algorithm for Markov and i.i.d. rewards.

Algorithm tackles clustered contextual bandits with resource constraints.

The AlphaZero algorithm for the learning of strategy games via self-play, which has produced superhuman ability in the games of Go, chess, and shogi, uses a quantitative reward function for game outcomes, requiring the users of the algorithm to explicitly balance different components of the reward against each other, s…

Contextual bandits study how reward variance affects regret bounds.

Attackers can significantly reduce team rewards in cooperative multi-agent reinforcement learning.

Text generation is a crucial task in NLP. Recently, several adversarial generative models have been proposed to improve the exposure bias problem in text generation. Though these models gain great success, they still suffer from the problems of reward sparsity and mode collapse. In order to address these two problems, …

A new UCB policy improves reward-cost ratio estimation in budgeted MAB.

We consider the linear contextual bandit problem with resource consumption, in addition to reward generation. In each round, the outcome of pulling an arm is a reward as well as a vector of resource consumptions. The expected values of these outcomes depend linearly on the context of that arm. The budget/capacity const…

This paper studies poisoning attacks in episodic RL and discovers their effectiveness depends on reward bounds.

OP-GFNs sample candidates in order-preserving proportion to a learned reward function.

The multi-armed bandit (MAB) problem is a classic example of the exploration-exploitation dilemma. It is concerned with maximising the total rewards for a gambler by sequentially pulling an arm from a multi-armed slot machine where each arm is associated with a reward distribution. In static MABs, the reward distributi…

New MAB model incentivizes user arm-pulling with self-reinforcing preferences.

New insights into balancing reward and fairness in stochastic MAB.

New algorithm for RL with horizon-free reward-free exploration for linear MDPs.

The stochastic multi-armed bandit (MAB) problem is a common model for sequential decision problems. In the standard setup, a decision maker has to choose at every instant between several competing arms, each of them provides a scalar random variable, referred to as a "reward." Nearly all research on this topic consider…

In reinforcement learning the Q-values summarize the expected future rewards that the agent will attain. However, they cannot capture the epistemic uncertainty about those rewards. In this work we derive a new Bellman operator with associated fixed point we call the `knowledge values'. These K-values compress both the …

A new algorithm for offline RL with trajectory-wise reward reduces bias and variance errors.

Proposes BSI for valid statistical inference on bandit algorithms.

Automated algorithm selection and hyperparameter tuning facilitates the application of machine learning. Traditional multi-armed bandit strategies look to the history of observed rewards to identify the most promising arms for optimizing expected total reward in the long run. When considering limited time budgets and c…

A multi-player bandit system resists adversarial attacks with near-optimal regret.

Adaptive policies solve a linear program to maximize rewards while minimizing costs in sales with discounts.

New algorithm optimizes reward while ensuring safety in complex decision-making problems.

New algorithms for efficient learning with long-term rewards in contextual bandits.

A novel algorithm reduces communication costs in federated best arm identification.

Optimal algorithm for maximizing rewards in contextual bandits with resource constraints.

We propose and study the known-compensation multi-arm bandit (KCMAB) problem, where a system controller offers a set of arms to many short-term players for $T$ steps. In each step, one short-term player arrives to the system. Upon arrival, the player aims to select an arm with the current best average reward and receiv…

New algorithm learns optimal policy for average reward MDPs with sample complexity matching lower bound.

New algorithm tackles adversarial corruption in Lipschitz bandits with sub-linear regret.

New algorithm reduces regret and constraint violation in constrained bandit problems.

In this paper, we propose a methodology based on piece-wise homogeneous Markov chain for credit ratings and a multivariate model of the credit spreads to evaluate the financial risk in European Union (EU). Two main aspects are considered: how the financial risk is distributed among the European countries and how large …

This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning. We introduce a model, the selectron, that (i) arises as the fast time constant limit of leaky integrate-and-fire neurons equipped with spiking timing dependent plasticity (STDP) and (ii) is amenable to the…

New algorithms boost SAT solver performance by optimizing restart strategies.

Paper develops robust estimators and strategies for stochastic MABs with heavy-tailed rewards.

Investigates risk measures for DC pension decumulation.

Algorithm improves movie recommendation efficiency with fairness constraints.

Improved best-arm identification in correlated multi-armed bandits.

Logarithmic regret strategies for safe multi-armed bandits with safety risk constraints.

New algorithm for non-stationary bandits with slow drifts.

New algorithm identifies good arms with fewer samples when thresholds are close.

Stable GFlowNets prevent loss spikes and mode collapse in training.