相关论文: Baba in Wonderland: Online Self-Supervised Dynamic…

Complex, real-world domains may not be fully modeled for an agent, especially if the agent has never operated in the domain before. The agent's ability to effectively plan and act in such a domain is influenced by its knowledge of when it…

Offline Reinforcement learning is commonly used for sequential decision-making in domains such as healthcare and education, where the rewards are known and the transition dynamics $T$ must be estimated on the basis of batch data. A key…

Classical reinforcement learning assumes the agent interacts with a fixed environment whose behavior does not depend on the agent's policy. This assumption breaks down in non-realizable settings where other actors might anticipate the…

Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to adapt to new tasks without costly real-world interactions. However, while using imagined…

To reliably navigate ever-shifting real-world environments, agents must grapple with incomplete knowledge and adapt their behavior through experience. However, current evaluations largely focus on tasks that leave no ambiguity, and do not…

Symbolic world modeling requires inferring and representing an environment's transitional dynamics as an executable program. Prior work has focused on largely deterministic environments with abundant interaction data, simple mechanics, and…

Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based…

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

As learning-based robotic controllers are typically trained offline and deployed with fixed parameters, their ability to cope with unforeseen changes during operation is limited. Biologically inspired, this work presents a framework for…

We integrate dual-process theories of human cognition with evolutionary game theory to study the evolution of automatic and controlled decision-making processes. We introduce a model where agents who make decisions using either automatic or…

Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience can be acquired. This property makes these algorithms…

Reinforcement Learning (RL) algorithms are known to scale poorly to environments with many available actions, requiring numerous samples to learn an optimal policy. The traditional approach of considering the same fixed action space in…

This paper proposes an algorithm Alice having no access to the physics law of the environment, which is actually linear with stochastic noise, and learns to make decisions directly online without a training phase or a stable policy as…

World models improve a learning agent's ability to efficiently operate in interactive and situated environments. This work focuses on the task of building world models of text-based game environments. Text-based games, or interactive…

Real-world control applications in complex and uncertain environments require adaptability to handle model uncertainties and robustness against disturbances. This paper presents an online, output-feedback, critic-only, model-based…

To solve multi-step manipulation tasks in the real world, an autonomous robot must take actions to observe its environment and react to unexpected observations. This may require opening a drawer to observe its contents or moving an object…

We consider the problem of learning to map from natural language instructions to state transitions (actions) in a data-efficient manner. Our method takes inspiration from the idea that it should be easier to ground language to concepts that…

Real-world robots must operate under evolving dynamics caused by changing operating conditions, external disturbances, and unmodeled effects. These may appear as gradual drifts, transient fluctuations, or abrupt shifts, demanding real-time…

Interest in biologically inspired alternatives to backpropagation is driven by the desire to both advance connections between deep learning and neuroscience and address backpropagation's shortcomings on tasks such as online, continual…

Machine Learning, however popular and accessible, is computationally intensive and highly power-consuming, prompting interest in alternative physical implementations of learning tasks. We introduce a training scheme for physical systems…