Related papers: Improving Reward-Conditioned Policies for Multi-Ar…
This paper addresses the poor finite-horizon performance of existing online \emph{restless bandit} (RB) algorithms, which stems from the prohibitive sample complexity of learning a full \emph{Markov decision process} (MDP) for each agent.…
The goal of robust constrained reinforcement learning (RL) is to optimize an agent's performance under the worst-case model uncertainty while satisfying safety or resource constraints. In this paper, we demonstrate that strong duality does…
In cooperative multi-agent reinforcement learning, a collection of agents learns to interact in a shared environment to achieve a common goal. We propose the use of reward machines (RM) -- Mealy machines used as structured representations…
The safe application of reinforcement learning (RL) requires generalization from limited training data to unseen scenarios. Yet, fulfilling tasks under changing circumstances is a key challenge in RL. Current state-of-the-art approaches for…
We consider multi-dimensional Markov decision processes and formulate a long term discounted reward optimization problem. Two simulation based algorithms---Monte Carlo rollout policy and parallel rollout policy are studied, and various…
Current multi-armed bandit approaches in recommender systems (RS) have focused more on devising effective exploration techniques, while not adequately addressing common exploitation challenges related to distributional changes and item…
Reinforcement learning (RL) problems over general state and action spaces are notoriously challenging. In contrast to the tableau setting, one can not enumerate all the states and then iteratively update the policies for each state. This…
Contextual bandits are canonical models for sequential decision-making under uncertainty in environments with time-varying components. In this setting, the expected reward of each bandit arm consists of the inner product of an unknown…
We consider a stochastic multi-armed bandit setting and study the problem of constrained regret minimization over a given time horizon. Each arm is associated with an unknown, possibly multi-dimensional distribution, and the merit of an arm…
Reinforcement Learning (RL) for constrained MDPs (CMDPs) is an increasingly important problem for various applications. Often, the average criterion is more suitable than the discounted criterion. Yet, RL for average-CMDPs (ACMDPs) remains…
Reward-biased maximum likelihood estimation (RBMLE) is a classic principle in the adaptive control literature for tackling explore-exploit trade-offs. This paper studies the stochastic contextual bandit problem with general bounded reward…
Group Relative Policy Optimization (GRPO) was introduced and used recently for promoting reasoning in LLMs under verifiable (binary) rewards. We show that the mean + variance calibration of these rewards induces a weighted contrastive loss…
We propose and study a new model for reinforcement learning with rich observations, generalizing contextual bandits to sequential decision making. These models require an agent to take actions based on observations (features) with the goal…
Reinforcement learning often needs to deal with the exponential growth of states and actions when exploring optimal control in high-dimensional spaces (often known as the curse of dimensionality). In this work, we address this issue by…
We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy…
Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while…
We develop asymptotically optimal policies for the multi armed bandit (MAB), problem, under a cost constraint. This model is applicable in situations where each sample (or activation) from a population (bandit) incurs a known bandit…
Reinforcement Learning (RL) has been widely applied to many control tasks and substantially improved the performances compared to conventional control methods in many domains where the reward function is well defined. However, for many…
The problem of how to take the right actions to make profits in sequential process continues to be difficult due to the quick dynamics and a significant amount of uncertainty in many application scenarios. In such complicated environments,…
Policy-based reinforcement learning methods suffer from the policy collapse problem. We find valued-based reinforcement learning methods with {\epsilon}-greedy mechanism are capable of enjoying three characteristics, Closed-form Diversity,…