wassname/rl_2d_walker.js
1
0
Fork 0
mirror of https://github.com/wassname/rl_2d_walker.js.git synced 2026-09-09 11:33:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

misc

Browse Source
This commit is contained in:
wassname
2018-11-26 11:10:23 +08:00
parent 28486b91ff
commit 4794d34343
2 changed files with 14 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+13 -2
View File
@@ -20,5 +20,16 @@ TODO: Write usage instructions
## TODO
- display/save time for each agent
- display save loss curves
- make walker into an env, with reset, done etc
- display save loss curves... everything from info
- make diff env's, copy humanoidwalker, humanoid, learning2run etc
- display
- display/save time for each agent
- smile frown?
- save checkpoints
# Credits
- The walker code is adapted from <a href="http://rednuht.org/genetic_walkers/">http://rednuht.org/genetic_walkers/</a>
- The refinforcement learning code uses <a href="https://github.com/janhuenermann/neurojs">neurojs</a>
index.html
+1 -1
View File
@@ -24,7 +24,7 @@
<body>
<div id="main_holder">
<h1>Reinforcement Learning 2D Humanoid Walkers</h1>
<h3 id="page_quote">"It's like watching robots breakdance"</h3>
<h3 id="page_quote">"Play that funky music robot"</h3>
<canvas id="main_screen" width="800" height="350"></canvas>
<div id="generation_timer"><div id="generation_timer_bar">&nbsp;</div></div>