Related papers: Success in Humanoid Reinforcement Learning under P…

We study a pursuit-evasion game between two players with car-like dynamics and sensing limitations by formalizing it as a partially observable stochastic zero-sum game. The partial observability caused by the sensing constraints is…

Learning good representations of historical contexts is one of the core challenges of reinforcement learning (RL) in partially observable environments. While self-predictive auxiliary tasks have been shown to improve performance in fully…

Training manipulation policies for humanoid robots with diverse data enhances their robustness and generalization across tasks and platforms. However, learning solely from robot demonstrations is labor-intensive, requiring expensive…

The deployment of humanoid robots in unstructured, human-centric environments requires navigation capabilities that extend beyond simple locomotion to include robust perception, provable safety, and socially aware behavior. Current…

Policy gradient methods are an appealing approach in reinforcement learning because they directly optimize the cumulative reward and can straightforwardly be used with nonlinear function approximators such as neural networks. The two main…

The robustness of legged locomotion is crucial for quadrupedal robots in challenging terrains. Recently, Reinforcement Learning (RL) has shown promising results in legged locomotion and various methods try to integrate privileged…

Humanoid robots deployed in industrial environments are required to perform load-carrying transportation tasks that tightly couple locomotion and manipulation. However, achieving stable and robust locomotion under varying payloads and…

Reinforcement learning provides an appealing framework for robotic control due to its ability to learn expressive policies purely through real-world interaction. However, this requires addressing real-world constraints and avoiding…

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…

In this paper, we propose a novel Deep Reinforcement Learning approach to address the mapless navigation problem, in which the locomotion actions of a humanoid robot are taken online based on the knowledge encoded in learned models.…

Continual learning for reinforcement learning agents remains a significant challenge, particularly in preserving and leveraging existing information without an external signal to indicate changes in tasks or environments. In this study, we…

In contrast to quadruped robots that can navigate diverse terrains using a "blind" policy, humanoid robots require accurate perception for stable locomotion due to their high degrees of freedom and inherently unstable morphology. However,…

Assessing the systemic effects of uncertainty that arises from agents' partial observation of the true states of the world is critical for understanding a wide range of scenarios. Yet, previous modeling work on agent learning and…

A robot's instantaneous sensory observations do not always reveal task-relevant state information. Under such partial observability, optimal behavior typically involves explicitly acting to gain the missing information. Today's standard…

Robot assistants for older adults and people with disabilities need to interact with their users in collaborative tasks. The core component of these systems is an interaction manager whose job is to observe and assess the task, and infer…

Recent literature in the robotics community has focused on learning robot behaviors that abstract out lower-level details of robot control. To fully leverage the efficacy of such behaviors, it is necessary to select and sequence them to…

Recent advances in behavior cloning (BC) have enabled impressive visuomotor control policies. However, these approaches are limited by the quality of human demonstrations, the manual effort required for data collection, and the diminishing…

The process of robot design is a complex task and the majority of design decisions are still based on human intuition or tedious manual tuning. A more informed way of facing this task is computational design methods where design parameters…

For robotic vehicles to navigate safely and efficiently in pedestrian-rich environments, it is important to model subtle human behaviors and navigation rules (e.g., passing on the right). However, while instinctive to humans, socially…

We study Reinforcement Learning for partially observable dynamical systems using function approximation. We propose a new \textit{Partially Observable Bilinear Actor-Critic framework}, that is general enough to include models such as…