Discovery of Options via Meta-Learned Subgoals — mentioned by esac

Sat, 10 Jul 2021 17:53:11 GMT

>genetic algorithms combined with RL where the genetics determine the reward function. I have been working on this problem for years (2+ as researcher, 2 as PhD student). The main issue is that evolution is both massively parallel and had plenty of runtime to get to human level intelligence. The person that pushes this evolution/evolved reward point is Andrew G. Barto and his students/collaborators over the years. Satinder Singh in particular is actively working on gradient based algorithms to find rewards (e.g. https://arxiv.org/abs/2102.06741) > Maybe we need to frame RL goals in much more…

Paper and discussion history. A mention is not an endorsement.

Discovery of Options via Meta-Learned Subgoals · HackerPapers discussions

Discovery of Options via Meta-Learned Subgoals — mentioned by esac