## LESSWRONGLW

A variant of Christiano's IDA amenable to learning-theoretic analysis. We consider reinforcement learning with a set of observations and a set of actions, where the semantics of the actions is making predictions about future observations. (But, as opposed to vanilla sequence forecasting, making predictions affects the environment.) The reward function is unknown and unobservable, but it is known to satisfy two assumptions:

(i) If we make the null prediction always, the expected utility will be lower bounded by some constant.

(ii) If our predictions sample th