相关论文: One Step is Enough: Multi-Agent Reinforcement Lear…

Developing reinforcement learning algorithms that satisfy safety constraints is becoming increasingly important in real-world applications. In multi-agent reinforcement learning (MARL) settings, policy optimisation with safety awareness is…

Improving the multi-step reasoning ability of large language models (LLMs) with offline reinforcement learning (RL) is essential for quickly adapting them to complex tasks. While Direct Preference Optimization (DPO) has shown promise in…

Enhancing the reasoning capabilities of large language models effectively using reinforcement learning (RL) remains a crucial challenge. Existing approaches primarily adopt two contrasting advantage estimation granularities: token-level…

Large Language Models (LLMs) have demonstrated remarkable capabilities, enabling language agents to excel at single-turn tasks. However, their application to complex, multi-step, and long-horizon tasks remains challenging. While…

Although multi-step generative policies achieve strong performance in robotic manipulation by modeling multimodal action distributions, they require multi-step iterative denoising at inference time. Each action therefore needs tens to…

Electric autonomous vehicles (EAVs) are getting attention in future autonomous mobility-on-demand (AMoD) systems due to their economic and societal benefits. However, EAVs' unique charging patterns (long charging time, high charging…

We study reinforcement learning in hybrid discrete-continuous action spaces, such as settings where the discrete component selects a regime (or index) and the continuous component optimizes within it -- a structure common in robotics,…

Improving sample efficiency has been a longstanding goal in reinforcement learning. This paper proposes $\mathtt{VRMPO}$ algorithm: a sample efficient policy gradient method with stochastic mirror descent. In $\mathtt{VRMPO}$, a novel…

One of the main operational challenges faced by the operators of one-way car-sharing systems is to ensure vehicle availability across the regions of the service areas with uneven patterns of rental requests. Fleet balancing strategies are…

Advances in artificial intelligence (AI) including foundation models (FMs), are increasingly transforming human society, with smart city driving the evolution of urban living.Meanwhile, vehicle crowdsensing (VCS) has emerged as a key…

Real-time robotic control demands fast action generation. However, existing generative policies based on diffusion and flow matching require multi-step sampling, fundamentally limiting deployment in time-critical scenarios. We propose…

In heterogeneous multi-agent reinforcement learning (MARL), achieving monotonic improvement plays a pivotal role in enhancing performance. The HAPPO algorithm proposes a feasible solution by introducing a sequential update scheme, which…

Recent advances in group-based reinforcement learning (RL) have driven frontier large language models (LLMs) in single-turn tasks like mathematical reasoning. However, their scalability to multi-turn LLM agent training remains limited.…

In this paper, a learning-based optimal transportation algorithm for autonomous taxis and ridesharing vehicles is presented. The goal is to design a mechanism to solve the routing problem for multiple autonomous vehicles and multiple…

Multi-agent reinforcement learning (MARL) faces challenges in coordinating agents due to complex interdependencies within multi-agent systems. Most MARL algorithms use the simultaneous decision-making paradigm but ignore the action-level…

Reinforcement learning (RL) approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO. However, policy lag from distributed training architectures and differences between the training and inference…

We consider the distributed pose-graph optimization (PGO) problem, which is fundamental in accurate trajectory estimation in multi-robot simultaneous localization and mapping (SLAM). Conventional iterative approaches linearize a highly…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for post-training reasoning models. However, group-based methods such as Group Relative Policy Optimization (GRPO) face a critical dilemma in…

How to optimally dispatch orders to vehicles and how to tradeoff between immediate and future returns are fundamental questions for a typical ride-hailing platform. We model ride-hailing as a large-scale parallel ranking problem and study…

Multi-agent reinforcement learning (MARL) provides a framework for problems involving multiple interacting agents. Despite apparent similarity to the single-agent case, multi-agent problems are often harder to train and analyze…