Related papers: On the Guaranteed Almost Equivalence between Imita…

We propose a new framework for imitation learning -- treating imitation as a two-player ranking-based game between a policy and a reward. In this game, the reward agent learns to satisfy pairwise performance rankings between behaviors,…

We present a Learning from Demonstration (LfD) framework that achieves one-shot generalization in multi-stage, contact-rich manipulation tasks. Central to our approach is the utilization of environmental constraints as the inductive bias.…

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…

Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF), offering theoretical equivalence with simpler implementation. We prove this equivalence is conditional rather…

Expert demonstrations have proven an easy way to indirectly specify complex tasks. Recent algorithms even support extracting unambiguous formal specifications, e.g. deterministic finite automata (DFA), from demonstrations. Unfortunately,…

Learning from Demonstration (LfD) has shown to provide robots with fundamental motion skills for a variety of domains. Various branches of LfD research (e.g., learned dynamical systems and movement primitives) can generally be classified…

Given a dataset of expert trajectories, standard imitation learning approaches typically learn a direct mapping from observations (e.g., RGB images) to actions. However, such methods often overlook the rich interplay between different…

Imitation from observation is a computational technique that teaches an agent on how to mimic the behavior of an expert by observing only the sequence of states from the expert demonstrations. Recent approaches learn the inverse dynamics of…

Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires…

While Reinforcement Learning (RL) has been proven essential for tuning large language models (LLMs), it can lead to reward over-optimization (ROO). Existing approaches address ROO by adding KL regularization, requiring computationally…

The robotic handling of compliant and deformable food raw materials, characterized by high biological variation, complex geometrical 3D shapes, and mechanical structures and texture, is currently in huge demand in the ocean space,…

Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert…

We develop a simple framework to learn bio-inspired foraging policies using human data. We conduct an experiment where humans are virtually immersed in an open field foraging environment and are trained to collect the highest amount of…

The paradigm of learning-from-observation (LfO) enables a robot to learn how to perform actions by observing human-demonstrated actions. Previous research in LfO have mainly focused on the industrial domain which only consist of the…

Flexible manufacturing processes demand robots to easily adapt to changes in the environment and interact with humans. In such dynamic scenarios, robotic tasks may be programmed through learning-from-demonstration approaches, where a…

Imitation learning holds the promise of equipping robots with versatile skills by learning from expert demonstrations. However, policies trained on finite datasets often struggle to generalize beyond the training distribution. In this work,…

Learning from demonstration allows for rapid deployment of robot manipulators to a great many tasks, by relying on a person showing the robot what to do rather than programming it. While this approach provides many opportunities, measuring,…

With the fast improvement of machine learning, reinforcement learning (RL) has been used to automate human tasks in different areas. However, training such agents is difficult and restricted to expert users. Moreover, it is mostly limited…

Behavior cloning has shown promise for robot manipulation, but real-world demonstrations are costly to acquire at scale. While simulated data offers a scalable alternative, particularly with advances in automated demonstration generation,…

Imitation learning has unlocked the potential for robots to exhibit highly dexterous behaviours. However, it still struggles with long-horizon, multi-object tasks due to poor sample efficiency and limited generalisation. Existing methods…