Kalman Temporal Differences
Because reinforcement learning suffers from a lack of scalability, online value (and Q-) function approximation has received increasing interest this last decade. This contribution introduces a novel approximation scheme, namely the Kalman Temporal Differences (KTD) framework, that exhibits the following features: sample-efficiency, non-linear approximation, non-stationarity handling and uncertainty management. A first KTD-based algorithm is provided for deterministic Markov Decision Processes (MDP) which produces biased estimates in the case of stochastic transitions. Than the eXtended KTD framework (XKTD), solving stochastic MDP, is described. Convergence is analyzed for special cases for both deterministic and stochastic transitions. Related algorithms are experimented on classical benchmarks. They compare favorably to the state of the art while exhibiting the announced features.
Code (0)
등록된 구현이 없습니다.
Tasks
Managementreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Probabilistic Successor Representations with Kalman Temporal Differences
The effectiveness of Reinforcement Learning (RL) depends on an animal's ability to assign credit for rewards to the appropriate preceding stimuli. One aspect of understanding the neural underpinnings of this process invo…
Reinforcement LearningReinforcement Learning (RL)Trust Region Value Optimization using Kalman Filtering
Policy evaluation is a key process in reinforcement learning. It assesses a given policy using estimation of the corresponding value function. When using a parameterized function to approximate the value, it is common to…
Reinforcement LearningNumerical Gaussian process Kalman filtering for spatiotemporal systems
We present a novel Kalman filter for spatiotemporal systems called the numerical Gaussian process Kalman filter (GPKF). Numerical Gaussian processes have recently been introduced as a physics informed machine learning me…
BIG-bench Machine LearningGaussian ProcessesPhysics-informed machine learningDeepKalPose: An Enhanced Deep-Learning Kalman Filter for Temporally Consistent Monocular Vehicle Pose Estimation
This paper presents DeepKalPose, a novel approach for enhancing temporal consistency in monocular vehicle pose estimation applied on video through a deep-learning-based Kalman Filter. By integrating a Bi-directional Kalm…
Pose EstimationTime SeriesVehicle Pose EstimationDeep Kalman Filtering Network for Video Compression Artifact Reduction
When lossy video compression algorithms are applied, compression artifacts often appear in videos, making decoded videos unpleasant for human visual systems. In this paper, we model the video artifact reduction task as a…
Video Compression