Essays about: "Proximal Policy Optimization"
Showing result 1 - 5 of 16 essays containing the words Proximal Policy Optimization.
-
1. Deep reinforcement learning for automated building climate control
University essay from Linköpings universitet/Institutionen för datavetenskapAbstract : The building sector is the single largest contributor to greenhouse gas emissions, making it a natural focal point for reducing energy consumption. More efficient use of energy is also becoming increasingly important for property managers as global energy prices are skyrocketing. READ MORE
-
2. Control Method for an Automated Forest Machine Based on Deep Reinforcement Learning
University essay from KTH/Skolan för industriell teknik och management (ITM)Abstract : An automated forest machine was designed in order to improve the working environment of today’s forest machine operators. In order to realize the autonomous control of the forest machine, model-based methods such as A* and dynamic window were used in previous projects. READ MORE
-
3. Evaluating the effects of hyperparameter optimization in VizDoom
University essay from Högskolan i Skövde/Institutionen för informationsteknologiAbstract : Reinforcement learning is a machine learning technique in which an artificial intelligence agent is guided by positive and negative rewards to learn strategies. To guide the agent’s behavior in addition to the reward are its hyperparameters. These values control how the agent learns. READ MORE
-
4. Generating molecular synthesis schemes : A deep learning approach to generate synthesizable molecules
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : One key challenge of drug discovery is the generation of molecules that can be synthesised in laboratories. This project studies a neural network architecture that generates reaction schemes by choosing initial reactants from a set of commercial compounds and determines the intermediate reactions until a final product is found. READ MORE
-
5. Deep Reinforcement Learning Applied to an Image-Based Sensor Control Task
University essay from Linköpings universitet/InformationskodningAbstract : An intelligent sensor system has the potential of providing its operator with relevant information, lowering the risk of human errors, and easing the operator's workload. One way of creating such a system is by using reinforcement learning, and this thesis studies how reinforcement learning can be applied to a simple sensor control task within a detailed 3D rendered environment. READ MORE
