A spiking Transformer trained on A* maze demonstrations reaches 99.64% action accuracy on a custom 21x21 maze benchmark, but the energy-efficiency and baseline-comparison claims are not backed by proper experiments.
Title resolution pending
1 Pith paper cite this work, alongside 111 external citations. Polarity classification is still indexing.
1
Pith paper citing it
111
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Energy-Efficient Deep Reinforcement Learning with Spiking Transformers
A spiking Transformer trained on A* maze demonstrations reaches 99.64% action accuracy on a custom 21x21 maze benchmark, but the energy-efficiency and baseline-comparison claims are not backed by proper experiments.