IEEE

Actor–Critic Model Predictive Control: Differentiable Optimization Meets Reinforcement Learning for Agile Flight

Abstract: A key open challenge in agile quadrotor flight is how to combine the flexibility and task-level generality of model-free reinforcement learning (RL) with the structure and online replanning ...
Frontiers

A combined approach to lithology identification using reinforcement learning and transformer algorithms

Lithology identification plays a pivotal role in logging interpretation during drilling operations, directly influencing drilling decisions and efficiency. Conventional lithology identification ...
IEEE

AC4MPC: Actor-Critic Reinforcement Learning for Guiding Model Predictive Control

Abstract: Nonlinear model predictive control (MPC) and reinforcement learning (RL) are two powerful control strategies with complementary advantages. This work shows how actor-critic RL techniques can ...
AOL

Michael Stuhlbarg is an actor's actor. But he's still learning from the best.

Need to drop a levity bomb in the middle of a group of pretentious characters? Or give Julia Roberts or Tom Cruise a great scene partner? Call Michael Stuhlbarg. In the past 15 years, the Emmy- and ...
GitHub

RLAF: Reinforcement Learning from Agentic Feedback

Traditional RL uses single scalar rewards. RLAF uses multi-perspective critic ensembles: rlaf/ ├── agents/ # Actor and Critic agents │ ├── actor.py # Agent being trained │ └── critic.py # Evaluation ...
Frontiers

Deep Reinforcement Learning for complex hydropower management: evaluating Soft Actor-Critic with a learned system dynamics model

Introduction: Optimizing the operation of interconnected hydropower systems presents significant challenges due to complex non-linear dynamics, hydrological uncertainty, and the need to balance ...
GitHub

mfzhang/20250818-Portfolio-Management-ActorCriticRL

There was an error while loading. Please reload this page.
MIT Technology Review

Why we should thank pigeons for our AI breakthroughs

The bird has never gotten much credit for being intelligent. But the reinforcement learning powering the world’s most advanced AI systems is far more pigeon than human. In 1943, while the world’s ...