M3 trains one Mamba-based RL agent to size multiple analog circuits, mixing real and synthetic simulator data on a schedule, and reports roughly 10x better sample efficiency than SAC baselines.
On effective scheduling of model-based reinforcement learning,
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
-
M3: Mamba-assisted Multi-Circuit Optimization via MBRL with Effective Scheduling
M3 trains one Mamba-based RL agent to size multiple analog circuits, mixing real and synthetic simulator data on a schedule, and reports roughly 10x better sample efficiency than SAC baselines.