Deep reinforcement learning with incremental updates optimizes Rydberg CNOT gates to 0.9991 average fidelity by discovering smooth pulses and an early-cutoff policy.
The state vector and action space are expanded accordingly ⃗S(ti) = [ ρ(00) nn (ti), ρ(10) nn (ti) for n ∈ {1, 2, 3, 4}, Ωt(ti−1), ϕt(ti−1) ]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Intelligent Optimal Control of Rydberg Gates with Incremental-Update Deep Reinforcement Learning
Deep reinforcement learning with incremental updates optimizes Rydberg CNOT gates to 0.9991 average fidelity by discovering smooth pulses and an early-cutoff policy.