Related papers: Focused Skill Discovery: Learning to Control Speci…

In order to be effective general purpose machines in real world environments, robots not only will need to adapt their existing manipulation skills to new circumstances, they will need to acquire entirely new skills on-the-fly. A great…

The optimal way for a deep reinforcement learning (DRL) agent to explore is to learn a set of skills that achieves a uniform distribution of states. Following this,we introduce DisTop, a new model that simultaneously learns diverse skills…

The learning efficiency and generalization ability of an intelligent agent can be greatly improved by utilizing a useful set of skills. However, the design of robot skills can often be intractable in real-world applications due to the…

Deep reinforcement learning has achieved many impressive results in recent years. However, tasks with sparse rewards or long horizons continue to pose significant challenges. To tackle these important problems, we propose a general…

Learning diverse skills is one of the main challenges in robotics. To this end, imitation learning approaches have achieved impressive results. These methods require explicitly labeled datasets or assume consistent skill execution to enable…

Many high-performance human activities are executed with little or no external feedback: think of a figure skater landing a triple jump, a pitcher throwing a curveball for a strike, or a barista pouring latte art. To study the process of…

In complex manipulation scenarios (e.g. tasks requiring complex interaction of two hands or in-hand manipulation), generalization is a hard problem. Current methods still either require a substantial amount of (supervised) training data and…

The mastery of skills such as playing tennis or balancing an inverted pendulum implies a very accurate control of movements to achieve the task goals. Traditional accounts of skilled action control that focus on either routinization or…

Solving complex problems using reinforcement learning necessitates breaking down the problem into manageable tasks and learning policies to solve these tasks. These policies, in turn, have to be controlled by a master policy that takes…

In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data. Deep policy optimization methods have achieved impressive results on…

The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…

Language-conditioned robotic skills make it possible to apply the high-level reasoning of Large Language Models (LLMs) to low-level robotic control. A remaining challenge is to acquire a diverse set of fundamental skills. Existing…

Decision-making in complex, continuous multi-task environments is often hindered by the difficulty of obtaining accurate models for planning and the inefficiency of learning purely from trial and error. While precise environment dynamics…

Safe reinforcement learning is a promising path toward applying reinforcement learning algorithms to real-world problems, where suboptimal behaviors may lead to actual negative consequences. In this work, we focus on the setting where…

Dynamic decisions are pivotal to economic policy making. We show how existing evidence from randomized control trials can be utilized to guide personalized decisions in challenging dynamic environments with budget and capacity constraints.…

Understanding physical phenomena is a key component of human intelligence and enables physical interaction with previously unseen environments. In this paper, we study how an artificial agent can autonomously acquire this intuition through…

Self-supervised learning aims to extract meaningful features from unlabeled data for further downstream tasks. In this paper, we consider classification as a downstream task in phase 2 and develop rigorous theories to realize the factors…

Complex systems in science and engineering sometimes exhibit behavior that changes across different regimes. Traditional global models struggle to capture the full range of this complex behavior, limiting their ability to accurately…

A practical approach to robot reinforcement learning is to first collect a large batch of real or simulated robot interaction data, using some data collection policy, and then learn from this data to perform various tasks, using offline…