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 41 for “"Temporal difference learning"”.
-
Temporal Difference Learning for Viscous Incompressible Flow
… minimized numerically through deep reinforcement learning. This methodology is well-suited for high dimensional PDEs over irregular domains, as it is mesh-free and sampling techniques can avoid the curse of dimensionality. The extension to computing viscous incompressible flow is done by first …
-
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
Modern offline reinforcement learning relies on massive datasets that exceed main memory, requiring out-of-core processing via sequential, cyclic data scans. However, this deterministic streaming violates the Markovian sampling assumptions of classical RL convergence theory. This thesis resolves …
-
Time Oriented Anytime Motion Planning with Temporal Difference Learning
… navigation phase can be posed as a reinforcement learning problem. In this work, we present a motion planner that can be trained to minimize the overall time spent on both computation and navigation. To this end, we utilize anytime motion planning techniques as well as reinforcement learning …
-
Off-Policy Temporal Difference Learning For Robotics And Autonomous Systems
Reinforcement learning (RL) is a rapidly advancing field with implications in autonomous vehicles, medicine, finance, along with several other applications. Particularly, off-policy temporal difference (TD) learning, a specific type of RL technique, has been widely used in a variety of autonomous …
-
Application of temporal difference learning to the game of Snake.
… 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 actor-critic architecture, computer players capable of playing the game of Snake can be …
-
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 …
-
Optimized Evacuations for Active Shooter Incidents to Improve Safety Outcomes
… both model-based and model-free reinforcement learning (RL) techniques. The problem is formulated as a Non-Homogeneous Semi-Markov Decision Process (NHSMDP), capturing the temporal and spatial dynamics of both evacuees and the shooter within a graph-based representation of building layouts. …
-
Design and implementation of general purpose reinforcement learning agents
… we can use ideas from the field of reinforcement learning, an approach with strong mathematical foundations and intriguing biological implications. The available reinforcement learning algorithms are powerful because of their generality: agents simply receive a scalar reward value representing …
-
Effective reinforcement learning for collaborative multi-agent domains
Online reinforcement learning (RL) in collaborative multi-agent domains is difficult in general. The number of available actions is exponential in the number of agents. This poses serious problems for online learning as exploration requirements are massive. Consequently, the learning system has …
-
Incorporation of supervised targets in deep reinforcement learning
… of deep neural networks to Reinforcement Learning (RL), there have been numerous advances in its application to complex subsequent decision making processes. However, the RL algorithms also suffer from many issues such as instability, high sensitivity to hyperparameters, and vast sample …
-
Approximate universal artificial intelligence and self-play learning for games
… theory was of any relevance to reinforcement learning practitioners. This work suggests that it is indeed relevant and worthy of future investigation. The second part of this thesis looks at self-play learning in two player, deterministic, adversarial turn-based games. The main contribution is …
-
Sparse Value Function Approximation for Reinforcement Learning
<p>A key component of many reinforcement learning (RL) algorithms is the approximation of the value function. The design and selection of features for approximation in RL is crucial, and an ongoing area of research. One approach to the problem of feature selection is to apply sparsity-inducing …
-
A formal investigation of dopamine’s role in Attention-Deficit/Hyperactive Disorder: evidence for asymmetrically effective reinforcement learning signals
… of each theory within the framework of temporal-difference learning, a reinforcement learning algorithm demonstrated to model midbrain dopamine activity. The results presented in this thesis suggest that neither theory provides a good account for the behaviour of children and animal …
-
Learning-based intelligent control and safety assurance of unmanned autonomous vehicles
… discounted NMPC. Time-varying LQR feedback and Temporal-Difference learning enable online adaptation of NMPC weights and safety hyperparameters, demonstrating superior safety-performance trade-offs under parametric mismatch and actuator noise. This work provides a coherent framework from …
-
Countering murphys law: the use of anticipation and improvisation via an episodic memory in support of intelligent robot behavior
… robots. Integrating multiple levels of machine learning techniques such as temporal difference learning, instance-based learning, and partially observable Markov decision process, aggregated episodic memories are processed in order to accomplish anticipation as well as improvisation. How this …
-
Finite-sample analysis for distributed and neural reinforcement learning
… a modular finite-sample theory for reinforcement learning under two realities of modern practice that challenge classical analysis: nonlinear function approximation and trajectory-based, temporally dependent data, including distributed and continuing settings. The central objective is to provide …
-
Investigating midbrain dopamine neuron dynamics during decision-making
… error, motor control and reinforcement learning. <br/><br/>Within this thesis, subpopulations of mDAN are classified based on their projection targets in the striatum and molecular marker profiles. In addition, the intracellular calcium sensor GCaMP6f was expressed in distinct mDAN …
Page 1 of 3