karpathy / karpathy/convnetjs

Reinforcement Learning basic sample not working

Open
#112 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
JavaScript
Stars
11.2k
Forks
2.1k
PR merge metrics
No merged PRs in 30d

Description

The basic example provided here does not seem to work because the output was always 0:
https://cs.stanford.edu/people/karpathy/convnetjs/docs.html

Proof:
I tried changing this line:
var reward = action === 0 ? 1.0 : 0.0;
into:
var reward = action === 1 ? 1.0 : 0.0;

*** and got the same result which is 0

Code Example:
/*START CODE*/
var brain = new deepqlearn.Brain(3, 2); // 3 inputs, 2 possible outputs (0,1)
var state = [Math.random(), Math.random(), Math.random()];
for(var k=0;k<10000;k++) {
var action = brain.forward(state); // returns index of chosen action
var reward = action === 0 ? 1.0 : 0.0;
brain.backward([reward]); // <-- learning magic happens here
state[Math.floor(Math.random()*3)] += Math.random()*2-0.5;
}
brain.epsilon_test_time = 0.0; // don't make any more random choices
brain.learning = false;
// get an optimal action from the learned policy
var action = brain.forward(state);
/*END CODE*/

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.