Related papers: Reinforcement Learning of Implicit and Explicit Co…
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…
We propose to directly map raw visual observations and text input to actions for instruction execution. While existing approaches assume access to structured environment representations or use a pipeline of separately trained models, we…
Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is…
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…
A characteristic of reinforcement learning is the ability to develop unforeseen strategies when solving problems. While such strategies sometimes yield superior performance, they may also result in undesired or even dangerous behavior. In…
As a step towards developing zero-shot task generalization capabilities in reinforcement learning (RL), we introduce a new RL problem where the agent should learn to execute sequences of instructions after learning useful skills that solve…
Many recent machine learning models rely on fine-grained dynamic control flow for training and inference. In particular, models based on recurrent neural networks and on reinforcement learning depend on recurrence relations, data-dependent…
Learning-based control methods typically assume stationary system dynamics, an assumption often violated in real-world systems due to drift, wear, or changing operating conditions. We study reinforcement learning for control under…
Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human…
Robotic systems are more present in our society everyday. In human-robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To increase action…
Reinforcement learning policies are typically represented by black-box neural networks, which are non-interpretable and not well-suited for safety-critical domains. To address both of these issues, we propose constrained normalizing flow…
Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mystery how rewards based solely on final outcomes can help overcome the long-horizon barrier…
Active nematics, formed from a liquid crystalline suspension of active force dipoles, are a paradigmatic active matter system whose study provides insights into how chemical driving produces the cellular mechanical forces essential for…
Reinforcement Learning faces an important challenge in partial observable environments that has long-term dependencies. In order to learn in an ambiguous environment, an agent has to keep previous perceptions in a memory. Earlier memory…
Cyber-physical systems, such as mobile robots, must respond adaptively to dynamic operating conditions. Effective operation of these systems requires that sensing and actuation tasks are performed in a timely manner. Additionally, execution…
Efficient exploration has presented a long-standing challenge in reinforcement learning, especially when rewards are sparse. A developmental system can overcome this difficulty by learning from both demonstrations and self-exploration.…
Large Language Models (LLMs) are increasingly relied upon for complex workflows, yet their ability to maintain flow of instructions remains underexplored. Existing benchmarks conflate task complexity with structural ordering, making it…
Recent work has shown that deep reinforcement-learning agents can learn to follow language-like instructions from infrequent environment rewards. However, this places on environment designers the onus of designing language-conditional…
Traditional supervised learning mostly works on individual tasks and requires training on a large set of task-specific examples. This paradigm seriously hinders the development of task generalization since preparing a task-specific example…
Compared to rigid robots that are generally studied in reinforcement learning, the physical characteristics of some sophisticated robots such as soft or continuum robots are higher complicated. Moreover, recent reinforcement learning…