English
Related papers

Related papers: Learning Model Preconditions for Planning with Mul…

200 papers

Model-based Deep Reinforcement Learning (RL) assumes the availability of a model of an environment's underlying transition dynamics. This model can be used to predict future effects of an agent's possible actions. When no such model is…

Machine Learning · Computer Science 2021-12-15 Andreas Sedlmeier , Michael Kölle , Robert Müller , Leo Baudrexel , Claudia Linnhoff-Popien

Applications of Reinforcement Learning (RL) in robotics are often limited by high data demand. On the other hand, approximate models are readily available in many robotics scenarios, making model-based approaches like planning a…

Artificial Intelligence · Computer Science 2021-11-16 Ingmar Schubert , Danny Driess , Ozgur S. Oguz , Marc Toussaint

Simulation has long been an essential part of testing autonomous driving systems, but only recently has simulation been useful for building and training self-driving vehicles. Vehicle behavioural models are necessary to simulate the…

Robotics · Computer Science 2019-10-23 Ao Li , Liting Sun , Wei Zhan , Masayoshi Tomizuka

A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the…

Machine Learning · Computer Science 2019-05-16 Kai Olav Ellefsen , Jim Torresen

In applications of dynamical systems, situations can arise where it is desired to predict the onset of synchronization as it can lead to characteristic and significant changes in the system performance and behaviors, for better or worse. In…

Adaptation and Self-Organizing Systems · Physics 2021-06-30 Huawei Fan , Ling-Wei Kong , Ying-Cheng Lai , Xingang Wang

Long-horizon embodied planning is challenging because the world does not only change through an agent's actions: exogenous processes (e.g., water heating, dominoes cascading) unfold concurrently with the agent's actions. We propose a…

Accurate knowledge of the atomistic transition pathways in materials and material surfaces is crucial for many material science problems. However, conventional simulation techniques used to find these transitions are extremely…

Materials Science · Physics 2026-05-01 Henry Tischler , Wenting Li , Qi Tang , Danny Perez , Thomas Vogel

Modern machine learning requires system designers to specify aspects of the learning pipeline, such as losses, architectures, and optimizers. Meta-learning, or learning-to-learn, instead aims to learn those aspects, and promises to unlock…

Machine Learning · Computer Science 2024-01-10 Louis Kirsch , James Harrison , Jascha Sohl-Dickstein , Luke Metz

Models play an essential role in the design process of cyber-physical systems. They form the basis for simulation and analysis and help in identifying design problems as early as possible. However, the construction of models that comprise…

To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deployment in the…

Robotics · Computer Science 2022-06-29 Philipp Wu , Alejandro Escontrela , Danijar Hafner , Ken Goldberg , Pieter Abbeel

An agent with an inaccurate model of its environment faces a difficult choice: it can ignore the errors in its model and act in the real world in whatever way it determines is optimal with respect to its model. Alternatively, it can take a…

Modeling how a robot interacts with the environment around it is an important prerequisite for designing control and planning algorithms. In fact, the performance of controllers and planners is highly dependent on the quality of the model.…

Machine Learning · Computer Science 2020-03-03 Clark Zhang , Arbaaz Khan , Santiago Paternain , Alejandro Ribeiro

In model-based reinforcement learning, the agent interleaves between model learning and planning. These two components are inextricably intertwined. If the model is not able to provide sensible long-term prediction, the executed planner…

Machine Learning · Statistics 2019-03-19 Nan Rosemary Ke , Amanpreet Singh , Ahmed Touati , Anirudh Goyal , Yoshua Bengio , Devi Parikh , Dhruv Batra

Personal robots assisting humans must perform complex manipulation tasks that are typically difficult to specify in traditional motion planning pipelines, where multiple objectives must be met and the high-level context be taken into…

Robotics · Computer Science 2019-03-21 Hejia Zhang , Eric Heiden , Stefanos Nikolaidis , Joseph J. Lim , Gaurav S. Sukhatme

Sequence modelling requires determining which past tokens are causally relevant from the context and their importance: a process inherent to the attention layers in transformers, yet whose underlying learned mechanisms remain poorly…

Machine Learning · Computer Science 2026-04-14 Francesco D'Angelo , Nicolas Flammarion

Developing fast surrogates for Partial Differential Equations (PDEs) will accelerate design and optimization in almost all scientific and engineering applications. Neural networks have been receiving ever-increasing attention and…

Machine Learning · Computer Science 2024-11-21 AmirPouya Hemmasian , Amir Barati Farimani

Robot learning of real-world manipulation tasks remains challenging and time consuming, even though actions are often simplified by single-step manipulation primitives. In order to compensate the removed time dependency, we additionally…

Robotics · Computer Science 2021-07-07 Lars Berscheid , Pascal Meißner , Torsten Kröger

Learning priors on trajectory distributions can help accelerate robot motion planning optimization. Given previously successful plans, learning trajectory generative models as priors for a new planning problem is highly desirable. Prior…

Robotics · Computer Science 2024-03-27 Joao Carvalho , An T. Le , Mark Baierl , Dorothea Koert , Jan Peters

An effective approach to solving long-horizon tasks in robotics domains with continuous state and action spaces is bilevel planning, wherein a high-level search over an abstraction of an environment is used to guide low-level…

Artificial Intelligence · Computer Science 2023-09-06 Nishanth Kumar , Willie McClinton , Rohan Chitnis , Tom Silver , Tomás Lozano-Pérez , Leslie Pack Kaelbling

Recent studies in interpretability have explored the inner workings of transformer models trained on tasks across various domains, often discovering that these networks naturally develop highly structured representations. When such…