Deep Reinforcement Learning at the Edge of the Statistical Precipice with Rishabh Agarwal - #559


Manage episode 320388280 series 2355587
Player FM과 저희 커뮤니티의 TWIML and Sam Charrington 콘텐츠는 모두 원 저작자에게 속하며 Player FM이 아닌 작가가 저작권을 갖습니다. 오디오는 해당 서버에서 직접 스트리밍 됩니다. 구독 버튼을 눌러 Player FM에서 업데이트 현황을 확인하세요. 혹은 다른 팟캐스트 앱에서 URL을 불러오세요.

Today we’re joined by Rishabh Agarwal, a research scientist at Google Brain in Montreal. In our conversation with Rishabh, we discuss his recent paper Deep Reinforcement Learning at the Edge of the Statistical Precipice, which won an outstanding paper award at the most recent NeurIPS conference. In this paper, Rishabh and his coauthors call for a change in how deep RL performance is reported on benchmarks when using only a few runs, acknowledging that typically, DeepRL algorithms are evaluated by the performance on a large suite of tasks. Using the Atari 100k benchmark, they found substantial disparities in the conclusions from point estimates alone versus statistical analysis. We explore the reception of this paper from the research community, some of the more surprising results, what incentives researchers have to implement these types of changes in self-reporting when publishing, and much more.

The complete show notes for this episode can be found at

604 에피소드