📄 index.html
字号:
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"><html> <head> <title>Reinforcement Learning Simulator -- User Manual</title> <style> div.footer { clear: both; text-align: center; } div.content { margin: 0px; MARGIN-RIGHT: 205px } div.menu { border: 1px ridge rgb(139, 139, 174); padding: 3px; background-color: rgb(204, 204, 255); float: right; } a, a:visited { color: rgb(51, 102, 102); font-family: Arial,Helvetica,sans-serif; font-size: small; line-height: 4px; } h1 { text-align: center; } h3 { background-color: rgb(204, 204, 255); color: rgb(60, 60, 75); letter-spacing: 1.2px; font-weight: normal; padding-left: 4px; } hr { color: rgb(204, 204, 255); } </style></head><body style="color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);"><h1>Reinforcement Learning</h1><div class="menu"><a href="index.html">Overview</a><br><a href="maze_editor.html">create your own maze</a> <br><a href="ValueIter.html">Value Iteration</a> <br><a href="PolicyIter.html">Policy Iteration</a> <br><a href="QLearning.html">Q-Learning</a> <br><a href="PSweeping.html">Prioritized Sweeping</a> <br></div><div class="content"><h3>Installation and Execution: </h3><p>This tool is know to work with Java Runtime Environment(JRE)1.4.2 and above.To install JRE1.4.2 and above visit <a href="http://java.sun.com" target="new">http://java.sun.com</a>.</p><p>Once java is installed and it is in path:<ol> <li>Extract RL_sim.zip to appropriate directory. </li> <li>On windows: Start command prompt,<br> <li>On Linux: Start shell.</li> <li>Change directory to directory where files are extracted. Then Change directory to go in RL_sim directory. <li>Execute the command <big style="color: rgb(0, 0, 153);">'java -jar rl_sim.jar'</big></li></ol> </p> <p>To create a shortcut on windows:<ol> <li> Right click on desktop, select new, select Shortcut. </li> <li> Copy command <big style="color: rgb(0, 0, 153);">'java -jar rl_sim.jar'</big> as location of item and click next. </li> <li> Specify RLSim as name of shortcut and click finish.</li> <li> Right click on the shortcut and select properties.</li> <li> In Start in box, specify the absolute path of directory in which RL_sim.jar exists.</li> <li> Press Apply and Ok. The shortcut is ready for use :) </li></ol></p><p>If you want to recompile and execute from the source code the mainclass is called <big style="color: rgb(0, 0, 153);">MainUI.java </big></p><h3>Rules of the Game</h3><p>The experimental setup consists of an agent moving in a discretestate space represented by a maze where each state is represented by a cell in the maze.The maze contains terminal states represented by goal states andobstacles represented by walls. The maze is bounded on all sides by walls.If the agent tries to transition from one state to another and hits a wall instead then the agent receives a positive penalty and stays in thesame state. There is a path cost of 1 unit associated with every transitionthat the agent makes from one state to another. The aim of the agent isto find that path to the goal state which has least cost associated with it.</p><p>To model the noise in the environment a parameter named ‘pjog’ is used. Each state has a finite number of successors, N. If in a particularstate s the agent decides to perform action a then the agent will end up inthe valid successor of s with a probability equal to (1-pjog) and end up inany one of the N-1 successors of that state with a probability equal to pjog/ (N-1).</p><p>For Q learning and prioritized sweeping another parameter, called ε,is used. This is specifically to implement the ε-greedy policy.Under this policy the agent decides to perform the best action with a probabilityof (1- ε) and performs any random action with a probability equal to ε/(N-1).<br><h3>Credits</h3><p>This tool has been developed by <a href="http://rohit.freeshell.org/" target="new">Rohit Kelkar</a> and <a href="http://vivekm.freeshell.org/" target="new">Vivek Mehta</a>,as part of the Extended Course Project forMS in Information Technology with specialization in Robotics Technology,at <a href="http://www.ri.cmu.edu">Robotics Institute</a>,<a href="http://www.cmu.edu">Carnegie Mellon University</a>.</p><p><b>Advisor: <a href="http://www-2.cs.cmu.edu/~awm/" target="new">Prof. Andrew Moore</a></b></p><h3>Contact</h3><p>For any query regarding this tool, send us an email.<br><a href="http://rohit.freeshell.org/" target="new">Rohit Kelkar</a>: rohitkelkar28 [AT] yahoo [DOT] com <br><a href="http://vivekm.freeshell.org/" target="new">Vivek Mehta</a>: vivekm [AT] gmail [DOT] com </p></div><div class="footer"><hr style="height: 1px; width: 70%;" noshade="noshade"></div></body></html>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -