Sökning: "reward function"
Visar resultat 1 - 5 av 85 uppsatser innehållade orden reward function.
1. Decreasing Training Time of Reinforcement Learning Agents for Remote Tilt Optimization using a Surrogate Neural Network Approximator
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : One possible application of reinforcement learning in the telecommunication field is antenna tilt optimization. However, one of key challenges we face is that the use of handcrafted simulators as environments to provide information for agents is often time-consuming regarding training reinforcement learning agents. LÄS MER
2. Smart Tracking for Edge-assisted Object Detection : Deep Reinforcement Learning for Multi-objective Optimization of Tracking-based Detection Process
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Detecting generic objects is one important sensing task for applications that need to understand the environment, for example eXtended Reality (XR), drone navigation etc. However, Object Detection algorithms are particularly computationally heavy for real-time video analysis on resource-constrained mobile devices. LÄS MER
3. Cooperative Modular Neural Networks for Artificial Intelligence in Games : A Comparison with A Monolithic Neural Network Regarding Technical Aspects and The Player Experience
Uppsats för yrkesexamina på avancerad nivå, Blekinge Tekniska Högskola/Fakulteten för datavetenskaperSammanfattning : Recent years have seen multiple machine-learning research projects concerning agents in video games. Yet, there is a disjoint between this academic research and the video game industry, evidenced by the fact that game developers still hesitate to use neural networks (NN) due to lack of clarity and control. LÄS MER
4. An operator theoretic approach to the Riemann Hypothesis
Master-uppsats, Lunds universitet/Matematik (naturvetenskapliga fakulteten); Lunds universitet/MatematikcentrumSammanfattning : In 2023 an operator theoretic approach to the Prime Number Theorem was introduced by Olsen. In this thesis this approach is examined and applied to give a new, operator theoretic, proof of a different version of the Prime Number Theorem and of the Prime Number Theorem for arithmetic progressions. LÄS MER
5. Machine Learning-Based Instruction Scheduling for a DSP Architecture Compiler : Instruction Scheduling using Deep Reinforcement Learning and Graph Convolutional Networks
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Instruction Scheduling is a back-end compiler optimisation technique that can provide significant performance gains. It refers to ordering instructions in a particular order to reduce latency for processors with instruction-level parallelism. LÄS MER