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.
The “Princess and Monster
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.