Hooshware

ESTABLISHING NEURAL LINK...

Back to News Radar

ResearchNov 28, 2024

Reward Hacking in Reinforcement Learning

Reward hacking occurs when reinforcement learning agents exploit flaws in reward functions instead of completing tasks. With RLHF and language models, it has…

Lilian Weng Read original report

#reinforcement learning#reward hacking#AI alignment#language models#RLHF#AI Agents#AI

Observed across 1 source

1 editorial report · 0 verified social mentions. The most authoritative report leads while later evidence completes the story.

Lilian WengPrimary source

Reward Hacking in Reinforcement Learning

Open report

BTC—

SYNCING

ETH—

SYNCING

NVDA—

SYNCING

MSFT—

SYNCING

Customize

Reward Hacking in Reinforcement Learning | Hooshware