TY  - RPRT
TI  - Correctness is its own reward: bootstrapping error signals in self-guided reinforcement learning
AU  - Gong, Z.
AU  - Duarte, F.
AU  - Mooney, R.
AU  - Pearson, J.
PY  - 2025
DO  - 10.1101/2025.07.18.665446
UR  - https://www.biorxiv.org/content/10.1101/2025.07.18.665446v1
ID  - 10.1101/2025.07.18.665446
ER  -