Related papers: Driving Intents Amplify Planning-Oriented Reinforc…

In recent years, reinforcement learning (RL) has gained increasing attention in control engineering. Especially, policy gradient methods are widely used. In this work, we improve the tracking performance of proximal policy optimization…

Modern action-conditioned video world models achieve strong short-horizon visual realism, yet remain unreliable on rare, interaction-critical transitions that dominate downstream planning and policy performance. Because passive…

Multi-objective reinforcement learning (MORL) is a structured approach for optimizing tasks with multiple objectives. However, it often relies on pre-defined reward functions, which can be hard to design for balancing conflicting goals and…

Realistic user simulation is crucial for training and evaluating multi-turn dialogue systems, yet creating simulators that accurately replicate human behavior remains a significant challenge. An effective simulator must expose the failure…

Although deep reinforcement learning (DRL) has shown promising results for autonomous navigation in interactive traffic scenarios, existing work typically adopts a fixed behavior policy to control social vehicles in the training…

This work studies the alignment of large language models with preference data from an imitation learning perspective. We establish a close theoretical connection between reinforcement learning from human feedback RLHF and imitation learning…

Deep reinforcement learning (DRL) has been proven its efficiency in capturing users' dynamic interests in recent literature. However, training a DRL agent is challenging, because of the sparse environment in recommender systems (RS), DRL…

Existing end-to-end autonomous driving methods typically rely on imitation learning (IL) but face a key challenge: the misalignment between open-loop training and closed-loop deployment. This misalignment often triggers driver-initiated…

Supervised fine-tuning (SFT) has become the de facto post-training strategy for large vision-language-action (VLA) models, but its reliance on costly human demonstrations limits scalability and generalization. We propose Probe, Learn,…

Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and diversity. While reinforcement learning (RL) has been used to…

Proactive Recommender Systems (PRSs) aim to guide user preference shift toward target items by generating paths of intermediate recommendations. Reinforcement learning (RL) provides a principled framework for optimizing such sequential…

Deep Reinforcement Learning has been successfully applied to learn robotic control. However, the corresponding algorithms struggle when applied to problems where the agent is only rewarded after achieving a complex task. In this context,…

End-to-end autonomous driving has emerged as a promising paradigm for directly mapping sensor inputs to planning maneuvers using learning-based modular integrations. However, existing imitation learning (IL)-based models suffer from…

Vision-Language-Action (VLA) models have demonstrated potential in autonomous driving. However, two critical challenges hinder their development: (1) Existing VLA architectures are typically based on imitation learning in open-loop setup…

Reward design has been one of the central challenges for real world reinforcement learning (RL) deployment, especially in settings with multiple objectives. Preference-based RL offers an appealing alternative by learning from human…

Inverse reinforcement learning (IRL) aims to learn a reward function and a corresponding policy that best fit the demonstrated trajectories of an expert. However, current IRL works cannot learn incrementally from an ongoing trajectory…

Reinforcement learning (RL) is the dominant paradigm for post-training large language models. However, in the online, on-policy setting, rollout generation dominates the computational cost of training. Group-based policy optimization…

The teleoperated driving (TD) scenario comes with stringent Quality of Service (QoS) communication constraints, especially in terms of end-to-end (E2E) latency and reliability. In this context, Predictive Quality of Service (PQoS), possibly…

Domain-Incremental Learning (DIL) enables vision models to adapt to changing conditions in real-world environments while maintaining the knowledge acquired from previous domains. Given privacy concerns and training time, Rehearsal-Free DIL…

Offline reinforcement learning (RL) aims to infer sequential decision policies using only offline datasets. This is a particularly difficult setup, especially when learning to achieve multiple different goals or outcomes under a given…