Search Results for author:
Found 23 papers, 2 papers with code
PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos
PhysPT exploits a Transformer encoder-decoder backbone to effectively learn human dynamics in a self-supervised manner.
UniDCP: Unifying Multiple Medical Vision-language Tasks via Dynamic Cross-modal Learnable Prompts
Medical vision-language pre-training (Med-VLP) models have recently accelerated the fast-growing medical diagnostics application.
A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces
We study the global convergence of a Fisher-Rao policy gradient flow for infinite-horizon entropy-regularised Markov decision processes with Polish state and action space.
An Offline Learning Approach to Propagator Models
We show that a trader who tries to minimise her execution costs by using a greedy strategy purely based on the estimated propagator will encounter suboptimality due to so-called spurious correlation between the trading strategy and the estimator and due to intrinsic uncertainty resulting from a biased cost functional.
Insurance pricing on price comparison websites via reinforcement learning
The emergence of price comparison websites (PCWs) has presented insurers with unique challenges in formulating effective pricing strategies.
Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstruction
While 3D body reconstruction methods have made remarkable progress recently, it remains difficult to acquire the sufficiently accurate and numerous 3D supervisions required for training.
A Neural RDE approach for continuous-time non-Markovian stochastic control problems
We propose a novel framework for solving continuous-time non-Markovian stochastic control problems by means of neural rough differential equations (Neural RDEs) introduced in Morrill et al. (2021).
Statistical Learning with Sublinear Regret of Propagator Models
For the exploration phase we propose a novel approach for non-parametric estimation of the price impact kernel by observing only the visible price process and derive sharp bounds on the convergence rate, which are characterised by the singularity of the propagator.
Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems
We study the global linear convergence of policy gradient (PG) methods for finite-horizon continuous-time exploratory linear-quadratic control (LQC) problems.
Decomposing User-APP Graph into Subgraphs for Effective APP and User Embedding Learning
In this paper, we formulate the APP-installation user embedding learning into a bipartite graph embedding problem.
Optimal scheduling of entropy regulariser for continuous-time linear-quadratic reinforcement learning
This work uses the entropy-regularised relaxed stochastic control perspective as a principled framework for designing reinforcement learning (RL) algorithms.
SolarGAN: Synthetic Annual Solar Irradiance Time Series on Urban Building Facades via Deep Generative Networks
Building Integrated Photovoltaics (BIPV) is a promising technology to decarbonize urban energy systems via harnessing solar energy available on building envelopes.
Linear convergence of a policy gradient method for some finite horizon continuous time control problems
Despite its popularity in the reinforcement learning community, a provably convergent policy gradient method for continuous space-time control problems with nonlinear state dynamics has been elusive.
Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models
We develop a probabilistic framework for analysing model-based reinforcement learning in the episodic setting.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
Model Pruning Based on Quantified Similarity of Feature Maps
In this paper, we propose a novel theory to find redundant information in three-dimensional tensors, namely Quantified Similarity between Feature Maps (QSFM), and utilize this theory to guide the filter pruning procedure.
Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls
We study finite-time horizon continuous-time linear-convex reinforcement learning problems in an episodic setting.
Understanding Deep Architecture with Reasoning Layer
Recently, there is a surge of interest in combining deep learning models with reasoning in order to handle more sophisticated learning tasks.
Learning the aerodynamic design of supercritical airfoils through deep reinforcement learning
The policy is then trained in environments based on surrogate models, of which the mean drag reduction of 200 airfoils can be effectively improved by reinforcement learning.
Computational Engineering, Finance, and Science Data Analysis, Statistics and Probability
Logarithmic regret for episodic continuous-time linear-quadratic reinforcement learning over a finite-time horizon
We study finite-time horizon continuous-time linear-quadratic reinforcement learning problems in an episodic setting, where both the state and control coefficients are unknown to the controller.
Understanding Deep Architectures with Reasoning Layer
Recently, there has been a surge of interest in combining deep learning models with reasoning in order to handle more sophisticated learning tasks.
Regularity and stability of feedback relaxed controls
This paper proposes a relaxed control regularization with general exploration rewards to design robust feedback controls for multi-dimensional continuous-time stochastic exit time problems.
A neural network based policy iteration algorithm with global $H^2$-superlinear convergence for stochastic games on domains
In this work, we propose a class of numerical schemes for solving semilinear Hamilton-Jacobi-Bellman-Isaacs (HJBI) boundary value problems which arise naturally from exit time problems of diffusion processes with controlled drift.
Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems
In this paper, we establish that for a wide class of controlled stochastic differential equations (SDEs) with stiff coefficients, the value functions of corresponding zero-sum games can be represented by a deep artificial neural network (DNN), whose complexity grows at most polynomially in both the dimension of the state equation and the reciprocal of the required accuracy.
