kuz/DeepMind-Atari-Deep-Q-Learner

Is there "trained" model?

Opened this issue · 7 comments

Since it costs a long time training (30hours on GPU) to get the smart model, would you please provide an already trained model file that I can run without training from beginning?
I only have a CPU laptop so it can't afford such a long time training.
Thanks a lot in advance!

I've been running for ~8 hours on my GTX 970 and it can achieve high score of 10. The network file has grew to 400MiB.

btw, it seems I cannot resume to train the model, even though I changed related fields in run_gpu.

My bad, I set the save_freq too small, so that the network is overwritten before being analyzed.

Could you specify how you resumed training on a network after stopping? Thanks

So , do we have a trained model under some non commercial or open source license ?

@jtgebert have you found anyway to resume training ?

Nope, I set this aside for a bit.