Multitask Preplay replays experience from pursued tasks as starting points for counterfactual simulation of unpursued tasks to learn predictive representations that support fast generalization in humans and machines.
When does model-based control pay off? PLoS computational biology , 12(8):e1005090
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Preemptive Solving of Future Problems: Multitask Preplay in Humans and Machines
Multitask Preplay replays experience from pursued tasks as starting points for counterfactual simulation of unpursued tasks to learn predictive representations that support fast generalization in humans and machines.