Go-Explore: a New Approach for Hard-Exploration Problems — mentioned by kywch

Thu, 01 Jan 2026 00:04:39 GMT

I think Go-Explore (https://arxiv.org/abs/1901.10995) is promising. It'll provide automatic scaffolding and prevent catastrophic forgetting. If one can frame the problem into a competition, then self-play has been shown to work repeatedly.

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

Go-Explore: a New Approach for Hard-Exploration Problems — mentioned by FlyingSaucer

Tue, 05 Jan 2021 12:57:28 GMT

This topic is extremely interesting, and good to see that experiments support it. In AI lens: In a way, you can compare this to novelty seeking and intelligent exploration which is quite an active field in Artificial Life and game AI[1]. If you find this interesting: Jeff Clune, Kenneth Stanley and Joel Lehman conducted interesting related research. Also, isn't this somehow related to the Free Energy principle by Karl Friston? If you look at entropy maximization as a way to minimize surprises. [1] : https://arxiv.org/abs/1901.10995

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

Go-Explore: a New Approach for Hard-Exploration Problems · HackerPapers discussions

Go-Explore: a New Approach for Hard-Exploration Problems — mentioned by kywch

Go-Explore: a New Approach for Hard-Exploration Problems — mentioned by FlyingSaucer