相关论文: Directly Forecasting Belief for Reinforcement Lear…

While deep reinforcement learning (RL) has been demonstrated effective in solving complex control tasks, sample efficiency remains a key challenge due to the large amounts of data required for remarkable performance. Existing research…

Many real-world sequential decision making problems are partially observable by nature, and the environment model is typically unknown. Consequently, there is great need for reinforcement learning methods that can tackle such problems given…

Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation, yet their iterative denoising process incurs high computational costs. Existing training-free acceleration methods rely on…

State resetting is a fundamental but often overlooked capability of simulators. It supports sample-based planning by allowing resets to previously encountered simulation states, and enables calibration of simulators using real data by…

In real-world reinforcement learning (RL) systems, various forms of {\it impaired observability} can complicate matters. These situations arise when an agent is unable to observe the most recent state of the system due to latency or lossy…

Vision-Language-Action (VLA) models have shown great potential in general robotic decision-making tasks via imitation learning. However, the variable quality of training data often constrains the performance of these models. On the other…

Action-conditioned robot world models generate future video frames of the manipulated scene given a robot action sequence, offering a promising alternative for simulating tasks that are difficult to model with traditional physics engines.…

Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffer from two critical reliability bottlenecks: (1) reward…

Decision-focused learning (DFL), which differentiates through the KKT conditions, has recently emerged as a powerful approach for predict-then-optimize problems. However, under probabilistic settings, DFL faces three major bottlenecks:…

Empowered by expressive function approximators such as neural networks, deep reinforcement learning (DRL) achieves tremendous empirical successes. However, learning expressive function approximators requires collecting a large dataset…

Recent studies in reinforcement learning (RL) have made significant progress by leveraging function approximation to alleviate the sample complexity hurdle for better performance. Despite the success, existing provably efficient algorithms…

Current Reinforcement Learning (RL) algorithms struggle with long-horizon tasks where time can be wasted exploring dead ends and task progress may be easily reversed. We develop the SPOT framework, which explores within action safety zones,…

Several real-world scenarios, such as remote control and sensing, are comprised of action and observation delays. The presence of delays degrades the performance of reinforcement learning (RL) algorithms, often to such an extent that…

Distribution system state estimation (DSSE) is paramount for effective state monitoring and control. However, stochastic outputs of renewables and asynchronous streaming of multi-rate measurements in practical systems largely degrade the…

Decision Transformer (DT), a trajectory modelling method, has shown competitive performance compared to traditional offline reinforcement learning (RL) approaches on various classic control tasks. However, it struggles to learn optimal…

Performative prediction is a framework that captures distribution shifts that occur during the training of machine learning models due to their deployment. As the trained model is used, data generation causes the model to evolve, leading to…

Reinforcement Learning (RL) can enable agents to learn complex tasks. However, it is difficult to interpret the knowledge and reuse it across tasks. Inductive biases can address such issues by explicitly providing generic yet useful…

Stochastic communication delays in teleoperation introduce signal discontinuities that undermine control stability and degrade control performance. Consequently, the conventional reinforcement learning (RL) methods struggle with the delayed…

When the agent's observations or interactions are delayed, classic reinforcement learning tools usually fail. In this paper, we propose a simple yet new and efficient solution to this problem. We assume that, in the undelayed environment,…

Recent works have shown that tackling offline reinforcement learning (RL) with a conditional policy produces promising results. The Decision Transformer (DT) combines the conditional policy approach and a transformer architecture, showing…