Fixed, untrained reservoirs outperform trained recurrent networks on four memory-based reinforcement learning tasks, with local connectivity giving the fastest learning.
echo state
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reservoir Computing for Fast, Simplified Reinforcement Learning on Memory Tasks
Fixed, untrained reservoirs outperform trained recurrent networks on four memory-based reinforcement learning tasks, with local connectivity giving the fastest learning.