John Schulman
@johnschulman2
@thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music
参加 May 2021
2.2K フォロー中 82.5K ファン
@nabeelqu A big part of the problem was that the agents had nothing to lose after they were firstflagPOISONED. In this paper, we propose the creation of multiple circles of Hell, preserving incentives even after damnation
もっと見る
