A composite CNN and multi-head value architecture, Aftab, improves buffer-free PQN on Atari-57 from 2.692 to 6.479 IQM human-normalized score, but its Procgen generalization advantage is fragile.
6th International Conference of Soft Computing and Pattern Recognition (SoCPaR) , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Aftab: A Comprehensive Benchmark of CNN Encoders and Advanced Value Functions in Parallelized Q-Networks
A composite CNN and multi-head value architecture, Aftab, improves buffer-free PQN on Atari-57 from 2.692 to 6.479 IQM human-normalized score, but its Procgen generalization advantage is fragile.