相关论文: Improving Regret Approximation for Unsupervised Dy…

Deep Reinforcement Learning has shown excellent performance in generating efficient solutions for complex tasks. However, its efficacy is often limited by static training modes and heavy reliance on vast data from stable environments. To…

The assessment of safety performance plays a pivotal role in the development and deployment of connected and automated vehicles (CAVs). A common approach involves designing testing scenarios based on prior knowledge of CAVs (e.g., surrogate…

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…

Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative decoding (SD) accelerates autoregressive generation in…

Auto-regressive sequence generative models trained by Maximum Likelihood Estimation suffer the exposure bias problem in practical finite sample scenarios. The crux is that the number of training samples for Maximum Likelihood Estimation is…

We introduce Unsupervised Partner Design (UPD) - a population-free, multi-agent reinforcement learning framework for robust ad-hoc teamwork that adaptively generates training partners without requiring pretrained partners or manual…

Reinforcement learning usually uses the feedback rewards of environmental to train agents. But the rewards in the actual environment are sparse, and even some environments will not rewards. Most of the current methods are difficult to get…

Learning a reward function from demonstrations suffers from low sample-efficiency. Even with abundant data, current inverse reinforcement learning methods that focus on learning from a single environment can fail to handle slight changes in…

In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent…

We study dynamic regret in online convex optimization, where the objective is to achieve low cumulative loss relative to an arbitrary benchmark sequence. By observing that competing with an arbitrary sequence of comparators…

The wider application of end-to-end learning methods to embodied decision-making domains remains bottlenecked by their reliance on a superabundance of training data representative of the target domain. Meta-reinforcement learning (meta-RL)…

Agentic Retrieval-Augmented Generation (Agentic RAG) enhances the processing capability for complex tasks through dynamic retrieval and adaptive workflows. Recent advances (e.g., Search-R1) have shown that outcome-supervised reinforcement…

A long line of works characterizes the sample complexity of regret minimization in sequential decision-making by min-max programs. In the corresponding saddle-point game, the min-player optimizes the sampling distribution against an…

Model-free reinforcement learning has emerged as a powerful method for developing robust robot control policies capable of navigating through complex and unstructured environments. The effectiveness of these methods hinges on two essential…

Received waveforms contain rich information for both range information and environment semantics. However, its full potential is hard to exploit under multipath and non-line-of-sight conditions. This paper proposes a deep generative model…

One of the most promising developments in computer vision in recent years is the use of generative neural networks for functionality condition-based 3D design reconstruction and generation. Here, neural networks learn dependencies between…

Applying deep reinforcement learning (RL) on real systems suffers from slow data sampling. We propose an enhanced generative adversarial network (EGAN) to initialize an RL agent in order to achieve faster learning. The EGAN utilizes the…

Most existing single image deraining methods require learning supervised models from a large set of paired synthetic training data, which limits their generality, scalability and practicality in real-world multimedia applications. Besides,…

We present an optimisation-based method for synthesising a dynamic regret optimal controller for linear systems with potentially adversarial disturbances and known or adversarial initial conditions. The dynamic regret is defined as the…

Unsupervised reinforcement learning (URL) poses a promising paradigm to learn useful behaviors in a task-agnostic environment without the guidance of extrinsic rewards to facilitate the fast adaptation of various downstream tasks. Previous…