forked from tinygrad/tinygrad
* create cache for q learning * make linter happy * global beam * where it belongs * bugfix * ditch the kopt, use the beam * faster lin and DEBUG=2 okay * remove kopt, move search to features
* create cache for q learning * make linter happy * global beam * where it belongs * bugfix * ditch the kopt, use the beam * faster lin and DEBUG=2 okay * remove kopt, move search to features