Related papers: Foundational Policy Acquisition via Multitask Lear…

Humans often think of complex tasks as combinations of simpler subtasks in order to learn those complex tasks more efficiently. For example, a backflip could be considered a combination of four subskills: jumping, tucking knees, rolling…

Mobile manipulation tasks remain one of the critical challenges for the widespread adoption of autonomous robots in both service and industrial scenarios. While planning approaches are good at generating feasible whole-body robot…

We propose a novel approach to learn goal-conditioned policies for locomotion in a batch RL setting. The batch data is collected by a policy that is not goal-conditioned. For the locomotion task, this translates to data collection using a…

The paper presents a complete pipeline for learning continuous motion control policies for a mobile robot when only a non-differentiable physics simulator of robot-terrain interactions is available. The multi-modal state estimation of the…

Reinforcement learning (RL) has significantly advanced the control of physics-based and robotic characters that track kinematic reference motion. However, methods typically rely on a weighted sum of conflicting reward functions, requiring…

The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are…

This work aims to learn how to perform complex robot manipulation tasks that are composed of several, consecutively executed low-level sub-tasks, given as input a few visual demonstrations of the tasks performed by a person. The sub-tasks…

Learning visuomotor policy for multi-task robotic manipulation has been a long-standing challenge for the robotics community. The difficulty lies in the diversity of action space: typically, a goal can be accomplished in multiple ways,…

Imitation learning is a popular paradigm to teach robots new tasks, but collecting robot demonstrations through teleoperation or kinesthetic teaching is tedious and time-consuming. In contrast, directly demonstrating a task using our human…

Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other…

Reinforcement learning presents an attractive paradigm to reason about several distinct aspects of sequential decision making, such as specifying complex goals, planning future observations and actions, and critiquing their utilities.…

Multi-goal policy learning for robotic manipulation is challenging. Prior successes have used state-based representations of the objects or provided demonstration data to facilitate learning. In this paper, by hand-coding a high-level…

This paper focuses on the problem of detecting and reacting to changes in the distribution of a sensorimotor controller's observables. The key idea is the design of switching policies that can take conformal quantiles as input, which we…

Transfer reinforcement learning aims to improve the sample efficiency of solving unseen new tasks by leveraging experiences obtained from previous tasks. We consider the setting where all tasks (MDPs) share the same environment dynamic…

We present a novel reinforcement learning based algorithm for multi-robot task allocation problem in warehouse environments. We formulate it as a Markov Decision Process and solve via a novel deep multi-agent reinforcement learning method…

We are interested in learning models of non-stationary environments, which can be framed as a multi-task learning problem. Model-free reinforcement learning algorithms can achieve good asymptotic performance in multi-task learning at a cost…

Despite growing interest in developing legged robots that emulate biological locomotion for agile navigation of complex environments, acquiring a diverse repertoire of skills remains a fundamental challenge in robotics. Existing methods can…

The flocking motion control is concerned with managing the possible conflicts between local and team objectives of multi-agent systems. The overall control process guides the agents while monitoring the flock-cohesiveness and localization.…

Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task. The limitation is due to the restricted model architecture related to fixed input and output dimensions.…

We study the problem of reinforcement learning for a task encoded by a reward machine. The task is defined over a set of properties in the environment, called atomic propositions, and represented by Boolean variables. One unrealistic…