Unsupervised Real-Time Control through Variational Empowerment
We introduce a methodology for efficiently computing a lower bound to empowerment, allowing it to be used as an unsupervised cost function for policy learning in real-time control. Empowerment, being the channel capacity between actions and states, maximises the influence of an agent on its near future. It has been shown to be a good model of biological behaviour in the absence of an extrinsic goal. But empowerment is also prohibitively hard to compute, especially in nonlinear continuous spaces. We introduce an efficient, amortised method for learning empowerment-maximising policies. We demonstrate that our algorithm can reliably handle continuous dynamical systems using system dynamics learned from raw data. The resulting policies consistently drive the agents into states where they can use their full potential.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Quantum device fine-tuning using unsupervised embedding learning
Quantum devices with a large number of gate electrodes allow for precise control of device parameters. This capability is hard to fully exploit due to the complex dependence of these parameters on applied gate voltages. …
Deep Recurrent Gaussian Process with Variational Sparse Spectrum Approximation
Modeling sequential data has become more and more important in practice. Some applications are autonomous driving, virtual sensors and weather forecasting. To model such systems so called recurrent models are used. In th…
Autonomous DrivingVariational InferenceWeather ForecastingControlling the Interaction Between Generation and Inference in Semi-Supervised Variational Autoencoders Using Importance Weighting
Even though Variational Autoencoders (VAEs) are widely used for semi-supervised learning, the reason why they work remains unclear. In fact, the addition of the unsupervised objective is most often vaguely described as a…
Sentiment AnalysisTopic ClassificationDeep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
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 InferenceMotion Manipulation via Unsupervised Keypoint Positioning in Face Animation
Face animation deals with controlling and generating facial features with a wide range of applications. The methods based on unsupervised keypoint positioning can produce realistic and detailed virtual portraits. However…
Representation Learning