相关论文: Learning Multimodal Behaviors from Scratch with Di…

Uncertainty quantification is one of the central challenges for machine learning in real-world applications. In reinforcement learning, an agent confronts two kinds of uncertainty, called epistemic uncertainty and aleatoric uncertainty.…

Real-world datasets collected from sensors or human inputs are prone to noise and errors, posing significant challenges for applying offline reinforcement learning (RL). While existing methods have made progress in addressing corrupted…

Dynamic hedging is a financial strategy that consists in periodically transacting one or multiple financial assets to offset the risk associated with a correlated liability. Deep Reinforcement Learning (DRL) algorithms have been used to…

This paper introduces DiffCarl, a diffusion-modeled carbon- and risk-aware reinforcement learning algorithm for intelligent operation of multi-microgrid systems. With the growing integration of renewables and increasing system complexity,…

Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for…

Learning rewards from expert videos offers an affordable and effective solution to specify the intended behaviors for reinforcement learning (RL) tasks. In this work, we propose Diffusion Reward, a novel framework that learns rewards from…

Diffusion policies have shown to be very efficient at learning complex, multi-modal behaviors for robotic manipulation. However, errors in generated action sequences can compound over time which can potentially lead to failure. Some…

Understanding the behavior of deep reinforcement learning (DRL) agents is crucial for improving their performance and reliability. However, the complexity of their policies often makes them challenging to understand. In this paper, we…

Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurrently, Reinforcement Learning (RL) has emerged as a vital tool for aligning generative models…

Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning. A key challenge, however, that is not addressed by many of these methods is multi-agent credit assignment: assessing…

Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with…

Decision-focused learning (DFL) integrates predictive modeling and optimization by training predictors to optimize the downstream decision target rather than merely minimizing prediction error. To date, existing DFL methods typically rely…

This work introduces DiffuseLoco, a framework for training multi-skill diffusion-based policies for dynamic legged locomotion from offline datasets, enabling real-time control of diverse skills on robots in the real world. Offline learning…

On-policy reinforcement learning (RL) algorithms have demonstrated great potential in robotic control, where effective exploration is crucial for efficient and high-quality policy learning. However, how to encourage the agent to explore the…

Diffusion large language models (dLLMs) are emerging as an efficient alternative to autoregressive models due to their ability to decode multiple tokens in parallel. However, aligning dLLMs with human preferences or task-specific rewards…

This paper presents a robust reinforcement learning algorithm called robust deterministic policy gradient (RDPG), which reformulates the H-infinity control problem as a two-player zero-sum dynamic game between a user and an adversary. The…

During initial iterations of training in most Reinforcement Learning (RL) algorithms, agents perform a significant number of random exploratory steps. In the real world, this can limit the practicality of these algorithms as it can lead to…

This paper develops the first policy gradient method with global optimality guarantee and complexity analysis for robust reinforcement learning under model mismatch. Robust reinforcement learning is to learn a policy robust to model…

Vision-language-action (VLA) models have shown strong generalization across tasks and embodiments; however, their reliance on large-scale human demonstrations limits their scalability owing to the cost and effort of manual data collection.…

Reinforcement learning (RL) shows great potential in sequential decision-making. At present, mainstream RL algorithms are data-driven, which usually yield better asymptotic performance but much slower convergence compared with model-driven…