Viewing profile — romerocesar

romerocesar

HN member

[ my public key: https://keybase.io/romerocesar; my proof: https://keybase.io/romerocesar/sigs/wWtoueOPJUB_svvO259z36F7JwboBT_lnbefGTRpGNg ]

comment
Comment #15287518
this enables RL research that supports multi-agent environments, multiple views (cameras) and doesn't need to pick between physics or graphics because a game engine can do both! th…

Tue, Sep 19, 2017, 6:36 PM UTC
comment
Comment #13548249
The world is amazing

Thu, Feb 02, 2017, 5:02 AM UTC
comment
Comment #11678522
srsly? all the discussion above 10hrs+ before your comment and that's your question? RTFM: https://github.com/amznlabs/amazon-dsstne/blob/master/FAQ.md

Wed, May 11, 2016, 7:35 PM UTC
comment
Comment #11672168
One important difference is model-parallel training. From the FAQ: DSSTNE instead uses “model-parallel training”, where each layer of the network is split across the available GPUs…

Wed, May 11, 2016, 2:08 AM UTC