DiscoverAlignment Newsletter PodcastAlignment Newsletter #161: Creating generalizable reward functions for multiple tasks by learning a model of functional similarity
Alignment Newsletter #161: Creating generalizable reward functions for multiple tasks by learning a model of functional similarity

Alignment Newsletter #161: Creating generalizable reward functions for multiple tasks by learning a model of functional similarity

Update: 2021-08-20
Share

Description

Recorded by Robert Miles: http://robertskmiles.com

More information about the newsletter here: https://rohinshah.com/alignment-newsletter/

YouTube Channel: https://www.youtube.com/channel/UCfGGFXwKpr-TJ5HfxEFaFCg

Comments 
loading
Top Podcasts
The Best New Comedy Podcast Right Now – June 2024The Best News Podcast Right Now – June 2024The Best New Business Podcast Right Now – June 2024The Best New Sports Podcast Right Now – June 2024The Best New True Crime Podcast Right Now – June 2024The Best New Joe Rogan Experience Podcast Right Now – June 20The Best New Dan Bongino Show Podcast Right Now – June 20The Best New Mark Levin Podcast – June 2024
In Channel
Alignment Newsletter #173: Recent language model results from DeepMind

Alignment Newsletter #173: Recent language model results from DeepMind

2022-07-2116:43

Alignment Newsletter #172: Sorry for the long hiatus!

Alignment Newsletter #172: Sorry for the long hiatus!

2022-07-0505:52

Alignment Newsletter #171: Disagreements between alignment "optimists" and "pessimists"

Alignment Newsletter #171: Disagreements between alignment "optimists" and "pessimists"

2022-01-2314:21

Alignment Newsletter #170: Analyzing the argument for risk from power-seeking AI

Alignment Newsletter #170: Analyzing the argument for risk from power-seeking AI

2021-12-0813:01

Alignment Newsletter #169: Collaborating with humans without human data

Alignment Newsletter #169: Collaborating with humans without human data

2021-11-2415:08

Alignment Newsletter #168: Four technical topics for which Open Phil is soliciting grant proposals

Alignment Newsletter #168: Four technical topics for which Open Phil is soliciting grant proposals

2021-10-2816:21

Alignment Newsletter #167: Concrete ML safety problems and their relevance to x-risk

Alignment Newsletter #167: Concrete ML safety problems and their relevance to x-risk

2021-10-2017:10

Alignment Newsletter #166: Is it crazy to claim we're in the most important century?

Alignment Newsletter #166: Is it crazy to claim we're in the most important century?

2021-10-0815:42

Alignment Newsletter #165: When large models are more likely to lie

Alignment Newsletter #165: When large models are more likely to lie

2021-09-2216:05

Alignment Newsletter #164: How well can language models write code?

Alignment Newsletter #164: How well can language models write code?

2021-09-1518:40

Alignment Newsletter #163: Using finite factored sets for causal and temporal inference

Alignment Newsletter #163: Using finite factored sets for causal and temporal inference

2021-09-0819:27

Alignment Newsletter #162: Foundation models: a paradigm shift within AI

Alignment Newsletter #162: Foundation models: a paradigm shift within AI

2021-08-2715:46

Alignment Newsletter #161: Creating generalizable reward functions for multiple tasks by learning a model of functional similarity

Alignment Newsletter #161: Creating generalizable reward functions for multiple tasks by learning a model of functional similarity

2021-08-2017:38

Alignment Newsletter #160: Building AIs that learn and think like people

Alignment Newsletter #160: Building AIs that learn and think like people

2021-08-1317:26

Alignment Newsletter #159: Building agents that know how to experiment, by training on procedurally generated games

Alignment Newsletter #159: Building agents that know how to experiment, by training on procedurally generated games

2021-08-0427:00

Alignment Newsletter #158: Should we be optimistic about generalization?

Alignment Newsletter #158: Should we be optimistic about generalization?

2021-07-2915:39

Alignment Newsletter #157: Measuring misalignment in the technology underlying Copilot

Alignment Newsletter #157: Measuring misalignment in the technology underlying Copilot

2021-07-2314:17

Alignment Newsletter #156: The scaling hypothesis: a plan for building AGI

Alignment Newsletter #156: The scaling hypothesis: a plan for building AGI

2021-07-1614:17

Alignment Newsletter #155: A Minecraft benchmark for algorithms that learn without reward functions

Alignment Newsletter #155: A Minecraft benchmark for algorithms that learn without reward functions

2021-07-0812:43

Alignment Newsletter #154: What economic growth theory has to say about transformative AI

Alignment Newsletter #154: What economic growth theory has to say about transformative AI

2021-06-3016:05

loading
Google Play
Download from Google Play
Castbox
Download from App Store
usUnited States
00:00
00:00
1.0x

0.5x

0.8x

1.0x

1.25x

1.5x

2.0x

3.0x

Sleep Timer

Off

End of Episode

5 Minutes

10 Minutes

15 Minutes

30 Minutes

45 Minutes

60 Minutes

120 Minutes

Alignment Newsletter #161: Creating generalizable reward functions for multiple tasks by learning a model of functional similarity

Alignment Newsletter #161: Creating generalizable reward functions for multiple tasks by learning a model of functional similarity

We and our partners use cookies to personalize your experience, to show you ads based on your interests, and for measurement and analytics purposes. By using our website and our services, you agree to our use of cookies as described in our Cookie Policy.