Comments (8)
Hi,
The car body and dashboards are usually omitted in experiments in deep (vision) reinforcement learning papers by Schmidhuber's team and Deepmind team. That's why I removed them from the screen.
Anyway, you can recover the car body by modifying 280th line of grscreen.cpp
for (i = 1; i < s->_ncars; i++) {
grDrawCar(cars[i], curCar, dispCam->getDrawCurrent(), dispCam->getDrawDriver(), s->currentTime, dispCam);
}
You should modify i =1 to i = 0. After the compile, you will be able to see the car body.
i=0 represent the first car, that is the agent. And other numbers are opponent cars.
For car mirrors, you should uncomment 361-366 lines in grscreen.cpp
/* MIRROR */
/*
if (mirrorFlag && curCam->isMirrorAllowed ()) {
mirrorCam->display ();
glViewport (scrx, scry, scrw, scrh);
}
*/
To show the map, tachometers etc. I remember that we should uncomment appropriate methods in 841-845 lines of cGrBoard::refreshBoard in grboard.cpp.
void cGrBoard::refreshBoard(tSituation *s, float Fps, int forceArcade, tCarElt *curr)
{
if (arcadeFlag || forceArcade) {
grDispArcade(curr, s);
} else {
//if (debugFlag) grDispDebug(Fps, curr);
if (GFlag) grDispGGraph(curr);
//if (boardFlag) grDispCarBoard(curr, s);
//if (leaderFlag) grDispLeaderBoard(curr, s);
//if (counterFlag) grDispCounterBoard2(curr);
}
//trackMap->display(curr, s, Winx, Winy, Winw, Winh);
}
from gym_torcs.
Hi
Thanks @ugo-nama-kun and @yanpanlau for the wonderful codes and explanations. I have finished training and I'd like to record a video with some of the basic sensor readings like speedometer etc. Please could you give detailed instructions on how to compile after making the changes.
You should modify i =1 to i = 0. After the compile, you will be able to see the car body.
i=0 represent the first car, that is the agent. And other numbers are opponent cars.
I'm relatively new to linux and it was with great difficulty I got all these components to work. I don't want to break it . Everything is installed inside an Anaconda environment.
Thanks!
from gym_torcs.
@arsenious Check this: https://github.com/ugo-nama-kun/gym_torcs/tree/master/vtorcs-RL-color
from gym_torcs.
Thanks
from gym_torcs.
i changed i=1 to i=0 but how can i re-compile the cpp file?
i just did "make" at vtorcs-RL-color but it doesn't show car
from gym_torcs.
@JungHY
You need to
make
sudo make install
sudo make datainstall
from gym_torcs.
@sunshineclt
Thanks i'll try it
from gym_torcs.
Hi
Thanks @ugo-nama-kun and @yanpanlau for the wonderful codes and explanations. I have finished training and I'd like to record a video with some of the basic sensor readings like speedometer etc. Please could you give detailed instructions on how to compile after making the changes.You should modify i =1 to i = 0. After the compile, you will be able to see the car body.
i=0 represent the first car, that is the agent. And other numbers are opponent cars.I'm relatively new to linux and it was with great difficulty I got all these components to work. I don't want to break it . Everything is installed inside an Anaconda environment.
Thanks!
Do you reproduce the model which is close to the model given by the author?According to the modification suggestions given in other issues, I have been able to train the model, but the car does not run very well. The car often goes out of the track and cannot return to the track. Do you have any good suggestions?
@arsenious
from gym_torcs.
Related Issues (20)
- Why was vtorcs not forked?
- How to get image observation as an RGB value array? HOT 5
- How to change the max speed?
- I find a question about track information that make me amazing today!
- Improve gym_torcs FPS HOT 2
- How can you ensure that your step reward is the true reward after the action?
- Not able to make in vtorcs HOT 9
- Error while validating the trained model
- Race Pos returned in snakeOil is different from Race Pos shown in the game.
- Getting Image data HOT 4
- How to reduce the screen FPS to 60fps?
- Putting ice on the Road.
- Problem with make in vtorcs HOT 2
- extract img is completely black in torcs
- vision=true,and 64x64 but ob.img can't get current information
- Can not build UDP connection with scr_server!
- freeglut (/usr/local/lib/torcs/torcs-bin): ERROR: Internal error <FBConfig with necessary capabilities not found> in function fgOpenWindow
- About image generation
- ALSA error when running snakeoil3_gym.py HOT 1
- About the visualize
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from gym_torcs.