A reinforcement learning update that adjusts each neuron's input-output sensitivity using TD error can replace external exploration noise and backpropagation through time in small actor-critic tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dynamic Reinforcement Learning for Actors
A reinforcement learning update that adjusts each neuron's input-output sensitivity using TD error can replace external exploration noise and backpropagation through time in small actor-critic tasks.