0 comments
Comments sorted by top scores.
comment by Michaël Trazzi (mtrazzi) · 2019-04-25T15:35:45.328Z · LW(p) · GW(p)
This thread is to discuss "How useful is quantilization for mitigating specification-gaming? (Ryan Carey, Apr. 2019, SafeML ICLR 2019 Workshop)"
comment by Michaël Trazzi (mtrazzi) · 2019-04-25T15:35:24.845Z · LW(p) · GW(p)
This thread is to discuss "Quantilizers (Michaël Trazzi & Ryan Carey, Apr. 2019, Github)".
comment by Michaël Trazzi (mtrazzi) · 2019-04-25T15:35:09.233Z · LW(p) · GW(p)
This thread is to discuss "When to use quantilization (Ryan Carey, Feb. 2019, LessWrong [LW · GW])"
comment by Michaël Trazzi (mtrazzi) · 2019-04-25T15:34:29.184Z · LW(p) · GW(p)
This thread is to discuss "Reinforcement Learning with a Corrupted Reward Channel (Tom Everitt; Victoria Krakovna; Laurent Orseau; Marcus Hutter; Shane Legg, Aug. 2017, arXiv; IJCAI)"
comment by Michaël Trazzi (mtrazzi) · 2019-04-25T15:33:58.640Z · LW(p) · GW(p)
This thread is to discuss "Thoughts on Quantilizers (Stuart Armstrong, Jan. 2017, Intelligent Agent)"
comment by Michaël Trazzi (mtrazzi) · 2019-04-25T15:33:25.030Z · LW(p) · GW(p)
This thread is to discuss "Another view of quantilizers: avoiding Goodhart's Law (Jessica Taylor, Jan. 2016, Intelligent Agent Foundations Forum)"
comment by Michaël Trazzi (mtrazzi) · 2019-04-25T15:32:49.221Z · LW(p) · GW(p)
This thread is to discuss "New paper: "Quantilizers" (Rob Bensinger, Nov. 2015, MIRI)"
comment by Michaël Trazzi (mtrazzi) · 2019-04-25T15:32:05.280Z · LW(p) · GW(p)
This thread is to discuss "Quantilizers: A Safer Alternative to Maximizers for Limited Optimization (MIRI; AAAI)"
comment by Michaël Trazzi (mtrazzi) · 2019-04-25T15:31:20.321Z · LW(p) · GW(p)
This thread is to discuss "Quantilizers maximize expected utility subject to a conservative cost constraint (Jessica Taylor, Sep. 2015, Intelligent Agent Foundation Forum)"
comment by Michaël Trazzi (mtrazzi) · 2019-04-25T15:27:38.617Z · LW(p) · GW(p)
This thread is for general comments about the LessWrong post "Notes on Quantilization [LW · GW]"