LESSWRONGTags
LW

Reward Functions

EditHistorySubscribe

Help improve this page (2 flags)

EditHistorySubscribe

Help improve this page (2 flags)

Reward Functions

Contributors

Posts tagged Reward Functions

5

376Reward is not the optimization target

2y

123

5

47Draft papers for REALab and Decoupled Approval on tampering

Jonathan Uesato, Ramana Kumar

4y

2

2

103Scaling Laws for Reward Model Overoptimization

leogao, John Schulman, Jacob_Hilton

2y

13

2

87Seriously, what goes wrong with "reward the agent when it makes you smile"?

TurnTrout, johnswentworth

2y

42

2

74Interpreting Preference Models w/ Sparse Autoencoders

Logan Riggs, Jannik Brinkmann

5mo

12

2

46Four usages of "loss" in AI

2y

18

2

40Intrinsic Drives and Extrinsic Misuse: Two Intertwined Risks of AI

1y

0

2

39Language Agents Reduce the Risk of Existential Catastrophe

cdkg, Simon Goldstein

1y

14

2

33When is reward ever the optimization target?

1mo

12

2

20$100/$50 rewards for good references

Stuart_Armstrong

3y

5

2

13Why we want unbiased learning processes

Stuart_Armstrong

7y

3

2

5Learning societal values from law as part of an AGI alignment strategy

2y

18

1

130Utility ≠ Reward

5y

24

1

78Reward hacking behavior can generalize across tasks

Kei, Isaac Dunn, Henry Sleight, Miles Turpin, evhub, Carson Denison, Ethan Perez

6mo

5

1

50Shutdown-Seeking AI

Simon Goldstein

1y

32