RoSE-Opt: Robust and Efficient Analog Circuit Parameter Optimization with Knowledge-infused Reinforcement Learning

TL;DR

RoSE-Opt is a novel framework combining domain knowledge, Bayesian optimization, and reinforcement learning to achieve robust, efficient, and Pareto-optimal analog circuit parameter optimization with fewer samples.

Contribution

It introduces a knowledge-infused BO-RL framework that enhances sample efficiency and robustness in analog circuit parameter optimization, including parasitic-aware device tuning.

Findings

Demonstrates superior sample efficiency and design success rate.

Achieves Pareto optimality in circuit performance.

Provides guidance on RL algorithm selection for circuit optimization.

Abstract

This paper proposes a learning framework, RoSE-Opt, to achieve robust and efficient analog circuit parameter optimization. RoSE-Opt has two important features. First, it incorporates key domain knowledge of analog circuit design, such as circuit topology, couplings between circuit specifications, and variations of process, supply voltage, and temperature, into the learning loop. This strategy facilitates the training of an artificial agent capable of achieving design goals by identifying device parameters that are optimal and robust. Second, it exploits a two-level optimization method, that is, integrating Bayesian optimization (BO) with reinforcement learning (RL) to improve sample efficiency. In particular, BO is used for a coarse yet quick search of an initial starting point for optimization. This sets a solid foundation to efficiently train the RL agent with fewer samples. Experimental evaluations on benchmarking circuits show promising sample efficiency, extraordinary figure-of-merit in terms of design efficiency and design success rate, and Pareto optimality in circuit performance of our framework, compared to previous methods. Furthermore, this work thoroughly studies the performance of different RL optimization algorithms, such as Deep Deterministic Policy Gradients (DDPG) with an off-policy learning mechanism and Proximal Policy Optimization (PPO) with an on-policy learning mechanism. This investigation provides users with guidance on choosing the appropriate RL algorithms to optimize the device parameters of analog circuits. Finally, our study also demonstrates RoSE-Opt's promise in parasitic-aware device optimization for analog circuits. In summary, our work reports a knowledge-infused BO-RL design automation framework for reliable and efficient optimization of analog circuits' device parameters.