讲解：VizDoom game engine、 FPS、Deadly CorridorProcessing|Web

The goal of this Assignment is to expose you to some of the delights ofbuilding machine agents for playing video games. For this purpose we will assume the Deadly Corridor task from the VizDoomgame engine. VizDoom is an open source port of the FPS title that provides several differenttask configurations as well as the death match for which the game is wellknown. What makes this platform interesting from a learning agent perspectiveis that the first person perspective renders the task partially observable, whereas most instances of the Atari arcade games provide full observability. The basic challenge of your Assignment is to demonstrate the application of avisual reinforcement learning agent on the specific instance of the DeadlyCorridor task.In order to get you started, we will provide a paper detailing the application ofthe Tangled Program Graph (TPG) framework for visual reinforcement learningto VizDoom. You will need to familiarize yourself with this reference. Two code bases for TPG are made available: ? Python maintained by Ryan Amaral with some FAQ. ? Java maintained by Robert Smith. o Windows OS compatible Eclipse package: Copy this into yourEclipse workspace folder and import the Assignment. You mightalso need to change the Java path to match your version of Java. o Once imported into Java, all the dependencies should beproperly set up and you should be able to drop the TPG sourceinto the Assignment. Then update your API execution file and 代做VizDoom game engine、代写 FPS、代itwill be able to see all the correct code/DLL paths without anyneed for additional setup. The deadly corridor task requires you to successfully collect the ‘armour’ in thelast of a sequential sequence of 3 rooms connected by short corridors, as perthe following figure:Your agent is spawn in the first room (LHS) and has to successfully pass theopponent agents present in each room in order to finally collect the armour(RHS). Given that you are using a TPG learning agent for this task, you willhave to consider how to provide rewards for achieving useful behaviours in thistask. One example might be to reward removing opponent agents from thegame as well as minimizing distance to the armour. Other factors might includereducing the cost (to character health) of being hit or experimenting withdifferent methods of reproduction. The baseline behaviour corresponds to an agent that dies in room 2, and isworth a grade of B-. You need do following task for this Assignment: ? Provide your code, and show outcomes from your Assignment. ? 4 page written report. Such a report needs to summarize the findings ofyour Assignment detailing what you have learn over the course of theAssignment. View this as an opportunity to pass on someimportant/pragmatic tricks of the trade and/or caveats you picked upover the course of the Assignment. With this in mind empericalevidence needs to be demonstrated to emphasize the significance ofyour findings/recommendations.转自：http://www.3daixie.com/contents/11/3444.html