Actor Critic Reinforcement Learning

Actor-critic reinforcement learning (RL) is a powerful framework for training agents to make optimal decisions in complex environments by simultaneously learning a policy (actor) and a value function (critic). Current research emphasizes improving sample efficiency and robustness through techniques like incorporating inductive biases (e.g., symmetries), integrating actor-critic methods with model predictive control (MPC), and utilizing hybrid approaches combining on-policy and off-policy learning, often employing deep neural networks such as convolutional and recurrent architectures. These advancements are driving progress in diverse fields, including robotics, autonomous systems, and financial modeling, by enabling the development of more efficient and reliable control policies for challenging real-world problems.

Papers

September 24, 2024

Autonomous Wheel Loader Navigation Using Goal-Conditioned Actor-Critic MPC
Aleksi Mäki-Penttilä, Naeim Ebrahimi Toulkani, Reza Ghabcheloo
Predictive Control Trajectory Optimization Actor Critic Reinforcement Learning

September 17, 2024

On-policy Actor-Critic Reinforcement Learning for Multi-UAV Exploration
Ali Moltajaei Farid, Jafar Roshanian, Malek Mouhoub
Proximal Policy Optimization Policy Reinforcement Learning Health Policy Recommendation Multiple Unmanned Aerial Vehicle Actor Critic Reinforcement Learning UAV Exploration

September 4, 2024

Surgical Task Automation Using Actor-Critic Frameworks and Self-Supervised Imitation Learning
Jingshuai Liu, Alain Andres, Yonghang Jiang, Xichun Luo, Wenmiao Shu, Sotirios Tsaftaris
Reinforcement Learning Imitation Learning Actor Critic Expert Demonstration Actor Critic Reinforcement Learning Surgical Automation

August 26, 2024

Equivariant Reinforcement Learning under Partial Observability
Hai Nguyen, Andrea Baisero, David Klee, Dian Wang, Robert Platt, Christopher Amato
Inductive Bias Inter Part Equivariance Partial Observability Actor Critic Reinforcement Learning Equivariant Filter

July 2, 2024

Generation of Geodesics with Actor-Critic Reinforcement Learning to Predict Midpoints
Kazumi Kasaura
Faithful Generation Actor Critic Shortest Path Generalized Geodesic Actor Critic Reinforcement Learning Global Path Planning Point Prediction Randomized Midpoint

June 6, 2024

AC4MPC: Actor-Critic Reinforcement Learning for Nonlinear Model Predictive Control
Rudolf Reiter, Andrea Ghezzi, Katrin Baumgärtner, Jasper Hoffmann, Robert D. McAllister, Moritz Diehl
Actor Critic Nonlinear Model Predictive Control Actor Critic Reinforcement Learning Control Architecture Control Strategy

June 5, 2024

Physics-Guided Actor-Critic Reinforcement Learning for Swimming in Turbulence
Christopher Koh, Laurent Pagnier, Michael Chertkov
Reinforcement Learning Actor Critic Algorithm Physical Reasoning Turbulent Flow Stratified Turbulence Actor Critic Reinforcement Learning

June 3, 2024

MOT: A Mixture of Actors Reinforcement Learning Method by Optimal Transport for Algorithmic Trading
Xi Cheng, Jinghao Zhang, Yunan Zeng, Wenfang Xue
Reinforcement Learning Optimal Transport Mixture Component Actor Critic Reinforcement Learning Market Data Algorithmic Trading

April 25, 2024

A Dual Perspective of Reinforcement Learning for Imposing Policy Constraints
Bram De Cooman, Johan Suykens
Reinforcement Learning Primal Dual Model Free Reinforcement Learning Multiple View Actor Critic Reinforcement Learning Policy Constraint

April 18, 2024

Actor-Critic Reinforcement Learning with Phased Actor
Ruofan Wu, Junmin Zhong, Jennie Si
Policy Gradient Actor Critic Actor Critic Reinforcement Learning Semantic Actor

February 5, 2024

Frugal Actor-Critic: Sample Efficient Off-Policy Deep Reinforcement Learning Using Unique Experiences
Nikhil Kumar Singh, Indranil Saha
Actor Critic Reinforcement Learning Policy Actor Critic Model Free Policy State Reward

December 17, 2023

CACTO-SL: Using Sobolev Learning to improve Continuous Actor-Critic with Trajectory Optimization
Elisa Alboni, Gianluigi Grandesso, Gastone Pietro Rosati Papini, Justin Carpentier, Andrea Del Prete
Reinforcement Learning Optimal Control Trajectory Optimization Actor Critic Dynamic Programming Actor Critic Reinforcement Learning Sobolev Training Cacto Sl

November 14, 2023

Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
Yifei Zhou, Ayush Sekhari, Yuda Song, Wen Sun
Policy Gradient Policy Optimization Offline Data Provable Guarantee Actor Critic Reinforcement Learning Hybrid Reinforcement Learning

October 20, 2023

Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesis
Philip John Gorinski, Matthieu Zimmer, Gerasimos Lampouras, Derrick Goh Xin Deik, Ignacio Iacobacci
Language Model Actor Critic Reinforcement Learning Code Synthesis

September 6, 2023

Addressing Imperfect Symmetry: a Novel Symmetry-Learning Actor-Critic Extension
Miguel Abreu, Luis Paulo Reis, Nuno Lau
Reinforcement Learning Actor Critic Actor Critic Reinforcement Learning Symmetric Model

June 16, 2023

Actor-Critic Model Predictive Control
Angel Romero, Yunlong Song, Davide Scaramuzza
Predictive Control Actor Critic Reinforcement Learning

June 14, 2023

A reinforcement learning strategy for p-adaptation in high order solvers
David Huergo, Gonzalo Rubio, Esteban Ferrer
Reinforcement Learning Proximal Policy Optimization Actor Critic Reinforcement Learning High Order Solver Mesh Adaptation

June 7, 2023

Adaptive Frequency Green Light Optimal Speed Advisory based on Hybrid Actor-Critic Reinforcement Learning
Ming Xu, Dongyu Zuo
Efficient Hybrid Actor Critic Reinforcement Learning Speed Advisory

January 30, 2023

Planning Multiple Epidemic Interventions with Reinforcement Learning
Anh Mai, Nikunj Gupta, Azza Abouzied, Dennis Shasha
Reinforcement Learning Markov Decision Process Optimal Planning Actor Critic Reinforcement Learning Disease Modeling

December 30, 2022

Asynchronous Hybrid Reinforcement Learning for Latency and Reliability Optimization in the Metaverse over Wireless Communications
Wenhan Yu, Terence Jie Chua, Jun Zhao
Reinforcement Learning Low Latency Ubiquitous Semantic Metaverse Actor Critic Reinforcement Learning Extended Reality Reliability Assessment Commitment