相关论文: Investigation on the generalization of the Sampled…

Offline policy evaluation (OPE) allows us to evaluate and estimate a new sequential decision-making policy's performance by leveraging historical interaction data collected from other policies. Evaluating a new policy online without a…

Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine the merits of both approaches by alternating between steps…

In many real recommender systems, novel items are added frequently over time. The importance of sufficiently presenting novel actions has widely been acknowledged for improving long-term user engagement. A recent work builds on Off-Policy…

Massive practical works addressed by Deep Q-network (DQN) algorithm have indicated that stochastic policy, despite its simplicity, is the most frequently used exploration approach. However, most existing stochastic exploration approaches…

Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network…

Projected policy gradient (PPG) is a basic policy optimization method in reinforcement learning. Given access to exact policy evaluations, previous studies have established the sublinear convergence of PPG for sufficiently small step sizes…

Projected Gradient Descent (PGD) is a strong and widely used first-order adversarial attack, yet its computational cost scales poorly, as all training samples undergo identical iterative inner-loop optimization despite contributing…

We show that on-policy policy gradient (PG) and its variance reduction variants can be derived by taking finite difference of function evaluations supplied by estimators from the importance sampling (IS) family for off-policy evaluation…

Learning optimal behavior from existing data is one of the most important problems in Reinforcement Learning (RL). This is known as "off-policy control" in RL where an agent's objective is to compute an optimal policy based on the data…

We study PCA as a stochastic optimization problem and propose a novel stochastic approximation algorithm which we refer to as "Matrix Stochastic Gradient" (MSG), as well as a practical variant, Capped MSG. We study the method both…

On-policy deep reinforcement learning remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are…

Reinforcement learning (RL) is about sequential decision making and is traditionally opposed to supervised learning (SL) and unsupervised learning (USL). In RL, given the current state, the agent makes a decision that may influence the next…

The study of decentralized learning or independent learning in cooperative multi-agent reinforcement learning has a history of decades. Recently empirical studies show that independent PPO (IPPO) can obtain good performance, close to or…

Stochastic optimization naturally appear in many application areas, including machine learning. Our goal is to go further in the analysis of the Stochastic Average Gradient Accelerated (SAGA) algorithm. To achieve this, we introduce a new…

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Deterministic-policy actor-critic algorithms for continuous control improve the actor by plugging its actions into the critic and ascending the action-value gradient, which is obtained by chaining the actor's Jacobian matrix with the…

In stochastic contextual bandit (SCB) problems, an agent selects an action based on certain observed context to maximize the cumulative reward over iterations. Recently there have been a few studies using a deep neural network (DNN) to…

In this paper, we propose a novel algorithm named STOchastic Recursive Momentum for Policy Gradient (STORM-PG), which operates a SARAH-type stochastic recursive variance-reduced policy gradient in an exponential moving average fashion.…

Independent on-policy policy gradient algorithms are widely used for multi-agent reinforcement learning (MARL) in cooperative and no-conflict games, but they are known to converge sub-optimally when each agent's individual policy gradient…

Although robotic applications increasingly demand versatile and dynamic object handling, most existing techniques are predominantly focused on grasp-based manipulation, limiting their applicability in non-prehensile tasks. To address this…