Related papers: Preference-Conditioned Multi-Objective RL for Inte…

Preference-based reinforcement learning (RL) offers a promising approach for aligning policies with human intent but is often constrained by the high cost of human feedback. In this work, we introduce PrefVLM, a framework that integrates…

Preference-based reinforcement learning (RL) provides a framework to train agents using human preferences between two behaviors. However, preference-based RL has been challenging to scale since it requires a large amount of human feedback…

Legged robots have enormous potential in their range of capabilities, from navigating unstructured terrains to high-speed running. However, designing robust controllers for highly agile dynamic motions remains a substantial challenge for…

Reinforcement learning (RL) methods for social robot navigation show great success navigating robots through large crowds of people, but the performance of these learning-based methods tends to degrade in particularly challenging or…

Stable locomotion in precipitous environments is an essential task for quadruped robots, requiring the ability to resist various external disturbances. Recent neural policies enhance robustness against disturbances by learning to resist…

This research note identifies a previously overlooked distinction between multi-objective reinforcement learning (MORL), and more conventional single-objective reinforcement learning (RL). It has previously been noted that the optimal…

We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execution uncertainty. The framework follows a closed-loop architecture that enables iterative…

Legged locomotion in unstructured environments demands not only high-performance control policies but also formal guarantees to ensure robustness under perturbations. Control methods often require carefully designed reference trajectories,…

The adoption of Reinforcement Learning (RL) in several human-centred applications provides robots with autonomous decision-making capabilities and adaptability based on the observations of the operating environment. In such scenarios,…

Learning-based methods have proven useful at generating complex motions for robots, including humanoids. Reinforcement learning (RL) has been used to learn locomotion policies, some of which leverage a periodic reward formulation. This work…

In recent years, reinforcement learning (RL) based quadrupedal locomotion control has emerged as an extensively researched field, driven by the potential advantages of autonomous learning and adaptation compared to traditional control…

Agile and adaptive maneuvers such as fall recovery, high-speed turning, and sprinting in the wild are challenging for legged systems. We propose a Curricular Hindsight Reinforcement Learning (CHRL) that learns an end-to-end tracking…

Humanoid robots are engineered to navigate terrains akin to those encountered by humans, which necessitates human-like locomotion and perceptual abilities. Currently, the most reliable controllers for humanoid motion rely exclusively on…

Unsupervised goal-conditioned reinforcement learning (GCRL) is a promising paradigm for developing diverse robotic skills without external supervision. However, existing unsupervised GCRL methods often struggle to cover a wide range of…

This thesis develops theoretical frameworks and algorithms that advance constrained reinforcement learning (RL) across control, preference learning, and alignment of large language models. The first contribution addresses constrained Markov…

Control policy learning for modular robot locomotion has previously been limited to proprioceptive feedback and flat terrain. This paper develops policies for modular systems with vision traversing more challenging environments. These…

Compared with single robots, Multi-Robot Systems (MRS) can perform missions more efficiently due to the presence of multiple members with diverse capabilities. However, deploying an MRS in wide real-world environments is still challenging…

We present a unified gait-conditioned reinforcement learning framework that enables humanoid robots to perform standing, walking, running, and smooth transitions within a single recurrent policy. A compact reward routing mechanism…

Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…

Preference-based reinforcement learning (RL) has emerged as a new field in robot learning, where humans play a pivotal role in shaping robot behavior by expressing preferences on different sequences of state-action pairs. However,…