Related papers: MoRe-ERL: Learning Motion Residuals using Episodic…
Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including competing objective balancing, low training…
Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…
This work introduces Transformer-based Off-Policy Episodic Reinforcement Learning (TOP-ERL), a novel algorithm that enables off-policy updates in the ERL framework. In ERL, policies predict entire action trajectories over multiple time…
As the demand for mobile robots continues to increase, social navigation has emerged as a critical task, driving active research into deep reinforcement learning (RL) approaches. However, because pedestrian dynamics and social conventions…
Human motion understanding and generation are crucial for vision and robotics but remain limited in reasoning capability and test-time planning. We propose MoRL, a unified multimodal motion model trained with supervised fine-tuning and…
This paper presents a novel approach that combines the advantages of both model-based and learning-based frameworks to achieve robust locomotion. The residual modules are integrated with each corresponding part of the model-based framework,…
Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data. Most existing offline RL algorithms use regularization or constraints to suppress extrapolation…
While search-augmented large language models (LLMs) exhibit impressive capabilities, their reliability in complex multi-hop reasoning remains limited. This limitation arises from three fundamental challenges: decomposition errors, where…
This study presents a dynamic safety margin-based reinforcement learning framework for local motion planning in dynamic and uncertain environments. The proposed planner integrates real-time trajectory optimization with adaptive gap…
Reinforcement learning (RL) has demonstrated compelling performance in robotic tasks, but its success often hinges on the design of complex, ad hoc reward functions. Researchers have explored how Large Language Models (LLMs) could enable…
In this paper, we explore the dynamic grasping of moving objects through active pose tracking and reinforcement learning for hand-eye coordination systems. Most existing vision-based robotic grasping methods implicitly assume target objects…
Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e.g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences.…
To support humanoid robots in performing manipulation tasks, it is essential to study stable standing while accommodating upper-body motions. However, the limited controllable range of humanoid robots in a standing position affects the…
We propose a control framework that integrates model-based bipedal locomotion with residual reinforcement learning (RL) to achieve robust and adaptive walking in the presence of real-world uncertainties. Our approach leverages a model-based…
Model-based offline reinforcement learning (MORL) aims to learn a policy by exploiting a dynamics model derived from an existing dataset. Applying conservative quantification to the dynamics model, most existing works on MORL generate…
Dynamic material handling (DMH) involves the assignment of dynamically arriving material transporting tasks to suitable vehicles in real time for minimising makespan and tardiness. In real-world scenarios, historical task records are…
Preference-aligned robot navigation in human environments is typically achieved through learning-based approaches, utilizing user feedback or demonstrations for personalization. However, personal preferences are subject to change and might…
Recent advances in large language models (LLMs) have enabled the development of autonomous agents capable of complex reasoning and multi-step problem solving. However, these agents struggle to adapt to specialized environments and do not…
Inspired by the impressive reasoning capabilities demonstrated by reinforcement learning approaches like DeepSeek-R1, recent emerging research has begun exploring the use of reinforcement learning (RL) to enhance vision-language models…
In cooperative multi-agent reinforcement learning (MARL), agents aim to achieve a common goal, such as defeating enemies or scoring a goal. Existing MARL algorithms are effective but still require significant learning time and often get…