IEEE

Single-Loop Deep Actor-Critic for Constrained Reinforcement Learning With Provable Convergence

Abstract: Deep actor-critic (DAC) algorithms, which combine actor-critic with deep neural network (DNN), have been among the most prevalent reinforcement learning algorithms for decision-making ...
GitHub

Train multi-step agents for real-world tasks using GRPO.

RULER (Relative Universal LLM-Elicited Rewards) eliminates the need for hand-crafted reward functions by using an LLM-as-judge to automatically score agent trajectories. Simply define your task in the ...
IEEE

A PVT-Robust Open-loop Gm-Ratio ×16 Gain Residue Amplifier for >1 GS/s Pipelined ADCs

Abstract: This work presents the design and simulation of a PVT-robust x16 gain dynamic open-loop inverter-based Gm-ratio residue-amplifier for high-speed SAR-assisted pipeline ADCs. The amplifier is ...