paper-with-me

홈 › Papers

Beta DVBF: Learning State-Space Models for Control from High Dimensional Observations

2019-11-02 · Neha Das, Maximilian Karl, Philip Becker-Ehmck, Patrick van der Smagt

Learning a model of dynamics from high-dimensional images can be a core ingredient for success in many applications across different domains, especially in sequential decision making. However, currently prevailing methods based on latent-variable models are limited to working with low resolution images only. In this work, we show that some of the issues with using high-dimensional observations arise from the discrepancy between the dimensionality of the latent and observable space, and propose solutions to overcome them.

📄 PDF Abstract BibTeX arXiv:1911.00756

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingSequential Decision MakingState Space Models

Similar Papers 제목 키워드 기반

Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data

2016-05-20 · Maximilian Karl, Maximilian Soelch, Justin Bayer, Patrick van der Smagt

We introduce Deep Variational Bayes Filters (DVBF), a new method for unsupervised learning and identification of latent Markovian state space models. Leveraging recent advances in Stochastic Gradient Variational Bayes, D…

State Space ModelsVariational Inference

Ball-and-socket joint pose estimation using magnetic field

2022-10-08 · Tai Hoang, Alona Kharchenko, Simon Trendel, Rafael Hostettler

Roboy 3.0 is an open-source tendon-driven humanoid robot that mimics the musculoskeletal system of the human body. Roboy 3.0 is being developed as a remote robotic body - or a robotic avatar - for humans to achieve remot…

Pose Estimation

Proximal Policy Optimization with Continuous Bounded Action Space via the Beta Distribution

2021-11-03 · Irving G. B. Petrazzini, Eric A. Antonelo

Reinforcement learning methods for continuous control tasks have evolved in recent years generating a family of policy gradient methods that rely primarily on a Gaussian distribution for modeling a stochastic policy. How…

continuous-controlContinuous ControlOpenAI GymPolicy Gradient Methods

Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates

2021-10-28 · Litian Liang, Yaosheng Xu, Stephen Mcaleer, Dailin Hu 외

Temporal-Difference (TD) learning methods, such as Q-Learning, have proven effective at learning a policy to perform control tasks. One issue with methods like Q-Learning is that the value update introduces bias when pre…

Q-LearningSchedulingState Estimation

BetaEdit: Null-Space Constrained Sequential Model Editing

2026-05-10 · Bingqing Liu, Wei Liu, Yuhua Li arxiv

Null-space-based methods have garnered considerable attention in model editing by constraining updates to the null space of the pre-existing knowledge representation, thereby preserving the model's original behavior. How…