arXiv research

Study optimal reward schemes for inducing desired player performance in risky contests.

This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show that a potential-based reward shaping scheme is able to preserve optimality of stochastic policies, and demonstrate that the ability of an a…

The paper proposes a model reward scheme for collaborative ML based on Shapley value and information gain.

Adaptive exploration scheme for evaluating multiple policies with different rewards.

New algorithm finds optimal policies without knowing reward functions.

Regularized policies are robust to adversarial rewards.

New method for LLMs to learn reasoning by optimizing latent variables.

One-bit feedback suffices for a bandit problem's optimal strategy.

Paper optimizes recommendation systems for long-term business metrics.

Reward collapse occurs when ranking-based reward models yield uniform rewards for different prompts.

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

New method tracks shifts in infinite-armed bandits without prior knowledge.

In this paper, we present a discrete-type approximation scheme to solve continuous-time optimal stopping problems based on fully non-Markovian continuous processes adapted to the Brownian motion filtration. The approximations satisfy suitable variational inequalities which allow us to construct $ε$-optimal stopping tim…

RL framework optimizes trading costs in noisy markets.

New algorithm for reward-free RL with linear function approximation, reducing sample complexity.

We consider the task of Inverse Reinforcement Learning in Contextual Markov Decision Processes (MDPs). In this setting, contexts, which define the reward and transition kernel, are sampled from a distribution. In addition, although the reward is a function of the context, it is not provided to the agent. Instead, the a…

New algorithm for collaborative bandit learning reduces sample complexity and regret.

A new insurance and reinsurance pricing scheme based on realized loss.

New algorithm for multi-player bandits with collision-dependent rewards.

New method for efficient online exploration in RLHF reduces regret.

This paper optimizes driver repositioning using MARL and reward design for better service and traffic management.

Study on private and robust multi-armed bandits with contaminated heavy-tailed rewards.

Improved DPO framework penalizes preference uncertainty to avoid overoptimization.

New $L_1$-Coverage objective simplifies exploration in reinforcement learning.

This work optimizes identifying good arms in nonparametric multi-armed bandits.

A scheme robust to action erasures improves MAB performance.

Efficiently learns matching rewards in two-sided markets with matrix completion.

New algorithm LOOP learns infinite-horizon AMDPs efficiently with function approximation.

Novel approach to contextual bandits using self-supervised learning.

This paper presents four different ways of looking at the well-known Least Squares Temporal Differences (LSTD) algorithm for computing the value function of a Markov Reward Process, each of them leading to different insights: the operator-theory approach via the Galerkin method, the statistical approach via instrumenta…

In light of the growing interest in agent-based market models, we bring together several earlier works in which we considered the topic of self-consistent market modelling. Building upon the binary game structure of Challet and Zhang, we discuss generalizations of the strategy reward scheme such that the agents seek to…

Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents. Motivated by decentralized applications such as sensor networks, swarm robotics, and power grids, we study policy evaluation in MARL, where agents with jo…

New algorithm uses Whittle index to improve Q-learning for restless bandits.

Shaping in humans and animals has been shown to be a powerful tool for learning complex tasks as compared to learning in a randomized fashion. This makes the problem less complex and enables one to solve the easier sub task at hand first. Generating a curriculum for such guided learning involves subjecting the agent to…

SA-GFN corrects biases in GFlowNets due to graph symmetries.

Local search improves GFlowNets' ability to generate high-reward samples.

Personalized recommendation systems (RS) are extensively used in many services. Many of these are based on learning algorithms where the RS uses the recommendation history and the user response to learn an optimal strategy. Further, these algorithms are based on the assumption that the user interests are rigid. Specifi…

EPIC quantifies reward differences without policy optimization.

Reward models need more than just accuracy for effective RLHF.

In a discounted reward Markov Decision Process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the Bellman equation and a fixed point iteration scheme known as the value iteration is u…

New method for optimizing risk in financial models using Fourier transforms.

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

Paper addresses reward hacking in preference optimization, proposing POWER-DL to improve AI alignment.

Manipulating data, such as weighting data examples or augmenting with new instances, has been increasingly used to improve model training. Previous work has studied various rule- or learning-based approaches designed for specific types of data manipulation. In this work, we propose a new method that supports learning d…

Paper proposes Langevin dynamics for adaptive IRL of stochastic gradient algorithms.

LinConTS improves regret and constraint violations in probabilistic linearly constrained bandits.

Adaptive RL optimizes testing resource allocation for dynamic software environments.

New method for RL with general utilities using variational policy gradient.