Related papers: Multi-Stage Manipulation with Demonstration-Augmen…

Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal. We extend the residual formulation to learn…

Recent high-capacity vision-language-action (VLA) models have demonstrated impressive performance on a range of robotic manipulation tasks by imitating human demonstrations. However, exploiting offline data with limited visited states will…

Model free reinforcement learning suffers from the high sampling complexity inherent to robotic manipulation or locomotion tasks. Most successful approaches typically use random sampling strategies which leads to slow policy convergence. In…

Modern deep learning models have demonstrated outstanding performance on discovering the underlying mechanisms when both visual appearance and intrinsic relations (e.g., causal structure) data are sufficient, such as Disentangled…

Explaining the behaviour of intelligent agents learned by reinforcement learning (RL) to humans is challenging yet crucial due to their incomprehensible proprioceptive states, variational intermediate goals, and resultant unpredictability.…

Learning continuous control in high-dimensional sparse reward settings, such as robotic manipulation, is a challenging problem due to the number of samples often required to obtain accurate optimal value and policy estimates. While many…

Many Reinforcement Learning (RL) approaches use joint control signals (positions, velocities, torques) as action space for continuous control tasks. We propose to lift the action space to a higher level in the form of subgoals for a motion…

We propose a Reinforcement Learning (RL) based control design framework for handling complex tasks. The approach extends the concept of Reward Machines (RM) with Signal Temporal Logic (STL) formulas that can be used for event generation.…

In this work, we focus on addressing the long-horizon manipulation tasks in densely cluttered scenes. Such tasks require policies to effectively manage severe occlusions among objects and continually produce actions based on visual…

Large Language Models (LLMs) have gained popularity in task planning for long-horizon manipulation tasks. To enhance the validity of LLM-generated plans, visual demonstrations and online videos have been widely employed to guide the…

Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-turn environments remains elusive. This…

Well-designed dense reward functions in robot manipulation not only indicate whether a task is completed but also encode progress along the way. Generally, designing dense rewards is challenging and usually requires access to privileged…

This paper presents a novel learning-based control framework that uses keyframing to incorporate high-level objectives in natural locomotion for legged robots. These high-level objectives are specified as a variable number of partial or…

Applying reinforcement learning (RL) to foreign exchange (Forex) trading remains challenging because realistic environments, well-defined reward functions, and expressive action spaces must be satisfied simultaneously, yet many prior…

The Reinforcement Learning (RL) paradigm has been an essential tool for automating robotic tasks. Despite the advances in RL, it is still not widely adopted in the industry due to the need for an expensive large amount of robot interaction…

Recently, quadrupedal locomotion has achieved significant success, but their manipulation capabilities, particularly in handling large objects, remain limited, restricting their usefulness in demanding real-world applications such as search…

Multi-step manipulation tasks in unstructured environments are extremely challenging for a robot to learn. Such tasks interlace high-level reasoning that consists of the expected states that can be attained to achieve an overall task and…

Reinforcement learning (RL) is a general and well-known method that a robot can use to learn an optimal control policy to solve a particular task. We would like to build a versatile robot that can learn multiple tasks, but using RL for each…

Acquiring complex behaviors is essential for artificially intelligent agents, yet learning these behaviors in high-dimensional settings poses a significant challenge due to the vast search space. Traditional reinforcement learning (RL)…

Reward machines (RMs) inform reinforcement learning agents about the reward structure of the environment. This is particularly advantageous for complex non-Markovian tasks because agents with access to RMs can learn more efficiently from…