Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 107 for “"Temporal-Difference"”.
-
Temporal Difference Learning for Viscous Incompressible Flow
This thesis presents a stochastic numerical method for computing viscous incompressible flow. By It\^o's lemma, the solution to a linear parabolic PDE is a martingale over an appropriate probability measure induced by Brownian motion. Given an initial boundary value problem, a functional …
-
Reducing sampling error in batch temporal difference learning
Temporal difference (TD) learning is one of the main foundations of modern reinforcement learning. This thesis studies the use of TD(0), a canonical TD algorithm, to estimate the value function of a given evaluation policy from a batch of data. In this batch setting, we show that TD(0) may converge …
-
Analysis of centralized and distributed temporal difference learning
Temporal difference learning with linear function approximation is a popular method to obtain a low-dimensional approximation of the value function of a policy in a Markov Decision Process. This thesis provides an interpretation of this method in terms of a splitting of the gradient of an …
-
Convergence analysis for out-of-core temporal difference learning
… by providing a novel convergence analysis of Temporal Difference (TD) learning under a cyclic streaming paradigm. Because cyclic scanning is deterministic, our analysis isolates and bounds the "intra-pass drift," the error introduced by continuously updating value estimates mid-scan. We …
-
Time Oriented Anytime Motion Planning with Temporal Difference Learning
Anytime algorithms are a class of algorithm which are interruptible and whose solution quality improves with time, tending towards an optimal solution. In other words, there is a non-decreasing relationship between time invested in computation and solution quality. Algorithms of this nature are …
-
Off-Policy Temporal Difference Learning For Robotics And Autonomous Systems
… other applications. Particularly, off-policy temporal difference (TD) learning, a specific type of RL technique, has been widely used in a variety of autonomous tasks. However, there remain significant challenges that must be overcome before it can be successfully applied to various real-world …
-
Application of temporal difference learning to the game of Snake.
The game of Snake has been selected to provide a unique application of the TD( ) algorithm as proposed by Sutton. A reinforcement learning technique for producing computer controlled players is documented. Using value function approximation with multilayer artificial neural networks and the …
-
Texplore : temporal difference reinforcement learning for robots and time-constrained domains
Robots have the potential to solve many problems in society, because of their ability to work in dangerous places doing necessary jobs that no one wants or is able to do. One barrier to their widespread deployment is that they are mainly limited to tasks where it is possible to hand-program …
-
Adaptive temporal difference learning of spatial memory in the water maze task
… the performance of a biologically inspired Temporal Difference (TD) approach to the learning of spatial memory for a robot in a dry version of the Morris water maze task. The Morris water maze task is a spatial memory task in which an association between cues from environment and position …
-
A Temporal Difference Representation for Temporal Profiling of Short Time Series Microarray Gene Expression Data
A novel method for temporal profiling of short time series microarray data, inspired by reconstructed phase space (RPS) theory and the minimum entropy clustering algorithm is introduced. The augmented first difference space provides addition information, relating to the trend of the time series, …
-
Source rate control in videoconferencing application using state–action–reward–state–action temporal difference reinforcement learning
… (SARSA) as a one-step Temporal Difference method, to control the source rate, while the other RL-based works on real-time communication apply function approximation (FA) as a way of learning the model. Although tabular RL approaches consume more memory space to store its …
-
Behavioral and Dorsomedial Striatal Dopamine Profiles in Context-Dependent Foraging Task Reflect Circular and Multi-Dimensional State Space in Temporal Difference Reinforcement Learning
… recalibrates local state valuation. Finally, temporal difference (TD) reinforcement learning simulations, which replicated the animals' exact behavioral trajectories, successfully reproduced the observed dopamine dynamics. Crucially, the sensitivity of TD-errors to context, mirroring that of …
-
Dinaminio programavimo taikymai Tetris žaidimui spręsti /
… of method properties. Using this chart three temporal difference‑based methods are chosen which allow to compare two method properties: batch and stochastic updates and also forward and backward returns. The experiments performed in the Tetris environment suggest that the use of stochastic …
-
Exploration of an unknown space by collective robotics using fuzzy logic and reinforcement learning
… viz: Heuristic Dynamic Programming (HDP) called Temporal Difference (TD(X)) method. The Temporal Difference method is an elegant way of doing reinforcement leaming. A simple ACD uses two neural networks, e.g., a criticand an action (control) network. The critic network leams to predict the total …
-
Optimized Evacuations for Active Shooter Incidents to Improve Safety Outcomes
… Decision Process (NHSMDP), capturing the temporal and spatial dynamics of both evacuees and the shooter within a graph-based representation of building layouts. Three major contributions are made: (1) the development of Naive ASTERS, a model-based RL algorithm that incorporates shooter …
-
Design and Analysis of Quantum Algorithms for Quantum Computing and Communications
… propose a new quantum algorithm of calculating temporal difference to detect the moving objects in any videos. Our quantum algorithm has the complexity of calculating temporal difference in dynamic video object detection to be only O(1). Secondly, we propose a new method to encode classical …
-
Adaptive dynamic programming with eligibility traces and complexity reduction of high-dimensional systems
… programming (DHP). Moreover, a one-step temporal-difference (TD(0)) and <em>n</em>-step TD (TD(λ)) with their gradients are utilized as learning algorithms to train and online-adapt the families of ADP. The dissertation is organized into seven papers. The first paper demonstrates the …
-
Design and implementation of general purpose reinforcement learning agents
… learning architecture. The final design uses temporal difference learning, radial basis functions, planning, uncertainty estimations, and curiosity. The main contributions of this thesis are: a novel combination of temporal difference learning with planning, uncertainty, and curiosity; a …
-
Improving Boundary Value Estimates at Domain Corners in a Reinforcement Learning based Elliptic PDE Solver
… and incorporate this method into an existing Temporal Difference (TD) learning algorithm for solving elliptic PDEs.
Page 1 of 6