相关论文: Bidirectional Soft Actor-Critic: Leveraging Forwar…

The actor-critic RL is widely used in various robotic control tasks. By viewing the actor-critic RL from the perspective of variational inference (VI), the policy network is trained to obtain the approximate posterior of actions given the…

Actor-critic algorithms have become a cornerstone in reinforcement learning (RL), leveraging the strengths of both policy-based and value-based methods. Despite recent progress in understanding their statistical efficiency, no existing work…

In this paper, we introduce a novel algorithm - the Skill-Driven Skill Recombination Algorithm (SDSRA) - an innovative framework that significantly enhances the efficiency of achieving maximum entropy in reinforcement learning tasks. We…

Trajectory Optimization (TO) and Reinforcement Learning (RL) offer complementary strengths for solving optimal control problems. TO efficiently computes locally optimal solutions but can struggle with non-convexity, while RL is more robust…

This work examines average-reward reinforcement learning with general policy parametrization. Existing state-of-the-art (SOTA) guarantees for this problem are either suboptimal or hindered by several challenges, including poor scalability…

High-precision control tasks present substantial challenges for reinforcement learning (RL) algorithms, frequently resulting in suboptimal performance attributed to network approximation inaccuracies and inadequate sample quality.These…

Recently, robust reinforcement learning (RL) methods designed to handle adversarial input observations have received significant attention, motivated by RL's inherent vulnerabilities. While existing approaches have demonstrated reasonable…

Trajectory Optimization (TO) and Reinforcement Learning (RL) are powerful and complementary tools to solve optimal control problems. On the one hand, TO can efficiently compute locally-optimal solutions, but it tends to get stuck in local…

Large language model (LLM) agents -- LLMs that dynamically interact with an environment over long horizons -- have become an increasingly important area of research, enabling automation in complex tasks involving tool-use, web browsing, and…

Control contraction metrics (CCMs) provide a framework to co-synthesize a controller and a corresponding contraction metric -- a positive-definite Riemannian metric under which a closed-loop system is guaranteed to be incrementally…

Compared to on-policy counterparts, off-policy model-free deep reinforcement learning can improve data efficiency by repeatedly using the previously gathered data. However, off-policy learning becomes challenging when the discrepancy…

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…

Recently many algorithms were devised for reinforcement learning (RL) with function approximation. While they have clear algorithmic distinctions, they also have many implementation differences that are algorithm-independent and sometimes…

Bus holding control is challenging due to stochastic traffic and passenger demand. While deep reinforcement learning (DRL) shows promise, standard actor-critic algorithms suffer from Q-value instability in volatile environments. A key…

Warm-Start reinforcement learning (RL), aided by a prior policy obtained from offline training, is emerging as a promising RL approach for practical applications. Recent empirical studies have demonstrated that the performance of Warm-Start…

Motion planning is the soul of robot decision making. Classical planning algorithms like graph search and reaction-based algorithms face challenges in cases of dense and dynamic obstacles. Deep learning algorithms generate suboptimal…

We present a non-asymptotic convergence analysis of $Q$-learning and actor-critic algorithms for robust average-reward Markov Decision Processes (MDPs) under contamination, total-variation (TV) distance, and Wasserstein uncertainty sets. A…

Online interactions with the environment to collect data samples for training a Reinforcement Learning (RL) agent is not always feasible due to economic and safety concerns. The goal of Offline Reinforcement Learning is to address this…

In recommendation systems, diversity and novelty are essential for capturing varied user preferences and encouraging exploration, yet many systems prioritize click relevance. While reinforcement learning (RL) has been explored to improve…

Training generative models to sample from unnormalized density functions is an important and challenging task in machine learning. Traditional training methods often rely on the reverse Kullback-Leibler (KL) divergence due to its…