paper-with-me

Papers

Predictive Control Using Learned State Space Models via Rolling Horizon Evolution

2021-06-25 · Alvaro Ovalle, Simon M. Lucas

A large part of the interest in model-based reinforcement learning derives from the potential utility to acquire a forward model capable of strategic long term decision making. Assuming that an agent succeeds in learning a useful predictive model, it still requires a mechanism to harness it to generate and select among competing simulated plans. In this paper, we explore this theme combining evolutionary algorithmic planning techniques with models learned via deep learning and variational inference. We demonstrate the approach with an agent that reliably performs online planning in a set of visual navigation tasks.

📄 PDF Abstract BibTeX arXiv:2106.13911

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingModel-based Reinforcement Learningreinforcement-learningReinforcement Learning (RL)State Space ModelsVariational InferenceVisual Navigation

Similar Papers 제목 키워드 기반

Deconfounded Lexicon Induction for Interpretable Social Science

2018-06-01 · NAACL 2018 6 · Reid Pryzant, Kelly Shen, Dan Jurafsky, Stefan Wagner

NLP algorithms are increasingly used in computational social science to take linguistic observations and predict outcomes like human preferences or actions. Making these social models transparent and interpretable often …

Keep it Simple: Data-efficient Learning for Controlling Complex Systems with Simple Models

2021-02-04 · Thomas Power, Dmitry Berenson

When manipulating a novel object with complex dynamics, a state representation is not always available, for example for deformable objects. Learning both a representation and dynamics from observations requires large amo…

Model Predictive Control

Reservoir Predictive Path Integral Control for Unknown Nonlinear Dynamics

2025-09-04 · Daisuke Inoue, Tadayoshi Matsumori, Gouhei Tanaka, Yuji Ito arxiv

Neural networks have found extensive application in data-driven control of nonlinear dynamical systems, yet fast online identification and control of unknown dynamics remain central challenges. To meet these challenges, …

Safe Imitation Learning of Nonlinear Model Predictive Control for Flexible Robots

2022-12-06 · Shamil Mamedov, Rudolf Reiter, Seyed Mahdi Basiri Azad, Ruan Viljoen 외

Flexible robots may overcome some of the industry's major challenges, such as enabling intrinsically safe human-robot collaboration and achieving a higher payload-to-mass ratio. However, controlling flexible robots is co…

Deformable Object ManipulationImitation LearningModel Predictive Control

Reinforcement Learning of the Prediction Horizon in Model Predictive Control

2021-02-22 · Eivind Bøhn, Sebastien Gros, Signe Moe, Tor Arne Johansen

Model predictive control (MPC) is a powerful trajectory optimization control technique capable of controlling complex nonlinear systems while respecting system constraints and ensuring safe operation. The MPC's capabilit…

Model Predictive ControlPredictionreinforcement-learningReinforcement Learning+1