mryellow
mryellow
Expert instruction is one application. Can forget whatever the net came up with and learn from experiences which have been overwritten with expert play, or some hand-crafted strategy. Last time...
Yeah no problem. Describing it just now, my method has always been a hack of discarding the agents selection after doing the unneeded work. Could pass a variable back toward...
> lag Not a lot happens before back to start of loop again. `next_action` might be as good as "do it 'now' given what I see this frame". It could...
Closing in favour of https://github.com/Kaixhin/Atari/pull/57 Avoids doing work only to then discard it.
Was thinking of adding the extra return to validation agents, allowing environment to pass back any change during validation also. However nothing is done with the action apart from acting....
Think I had some additional documentation changes to do on this. Been distracted working on hardware and getting dev environment fixed up, once that's outta the way will get this...
> In the readme can you add a line about how this doesn’t affect validation async/non-async? Will get to finishing this off soonish. https://gitter.im/Kaixhin/Atari?at=57cbda0bd52261ec345029ba
I believe this long-running request suffered the same issue but was misunderstood. https://github.com/mbenford/ngTagsInput/issues/418
This comment talks about Q promises being understood but normal Promises failing. Perhaps ties in here. https://github.com/mbenford/ngTagsInput/issues/135#issuecomment-41462315
Doable for simple lists of values without related ids. http://stackoverflow.com/a/17060235/2438830 This may suit my use-case as I'm using denormalised data and another copy of the name is no big deal....