Configuration entropy serves as a reliable proxy for the learned skills of reinforcement learning agents performing tasks in discrete space, validated through walker encounters and chess engine tests.
Underwater glider persistent coverage using deep reinforcement learning for ocean observation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.stat-mech 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Smart Walkers in Discrete Space
Configuration entropy serves as a reliable proxy for the learned skills of reinforcement learning agents performing tasks in discrete space, validated through walker encounters and chess engine tests.