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

317Reward is not the optimization target

1y

115

5

47Draft papers for REALab and Decoupled Approval on tampering

Jonathan Uesato, Ramana Kumar

3y

2

2

102Scaling Laws for Reward Model Overoptimization

leogao, John Schulman, Jacob_Hilton

1y

11

2

84Seriously, what goes wrong with "reward the agent when it makes you smile"?

TurnTrout, johnswentworth

1y

42

2

42Four usages of "loss" in AI

1y

18

2

30Language Agents Reduce the Risk of Existential Catastrophe

cdkg, Simon Goldstein

4mo

13

2

20$100/$50 rewards for good references

Stuart_Armstrong

2y

5

2

13Why we want unbiased learning processes

Stuart_Armstrong

6y

3

2

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

1y

18

1

48Shutdown-Seeking AI

Simon Goldstein

4mo

31

1

44A Short Dialogue on the Meaning of Reward Functions

Leon Lang, Quintin Pope, peligrietzer

10mo

0

1

30Thoughts on reward engineering

paulfchristiano

5y

30

1

26The reward engineering problem

paulfchristiano

5y

3

1

25Reward model hacking as a challenge for reward learning

1y

1

1

18Utility versus Reward function: partial equivalence

Stuart_Armstrong

5y

5