The work derives the optimal ratio of dynamics-to-reward samples that minimizes a bound on return error and characterizes the tradeoff between noisy but cheap rewards versus accurate but expensive ones in imagination-based policy optimization.
Reinforcement learning from human feedback trains reward models from preferences [Christiano et al., 2017, Stiennon et al., 2020], the empirical setting in which Gao et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On Training in Imagination
The work derives the optimal ratio of dynamics-to-reward samples that minimizes a bound on return error and characterizes the tradeoff between noisy but cheap rewards versus accurate but expensive ones in imagination-based policy optimization.