Neural Network Policy

Neural network policies are learned control strategies, often trained via reinforcement learning, that guide the behavior of autonomous systems. Current research emphasizes improving the safety, interpretability, and efficiency of these policies, focusing on techniques like decision trees for explainability, latent space manipulation for behavioral control, and the integration of large language models for high-level planning in multi-agent systems. These advancements are crucial for deploying reliable and trustworthy neural network controllers in safety-critical applications such as robotics and control systems, particularly in scenarios requiring robustness, adaptability, and human-understandable decision-making.

Papers

October 5, 2024

YOLO-MARL: You Only LLM Once for Multi-agent Reinforcement Learning
Yuan Zhuang, Yi Shen, Zhili Zhang, Yuxiao Chen, Fei Miao
Multi Agent Reinforcement Learning Multi Agent Multi Agent Reinforcement Neural Network Policy Strategy Synthesis

September 5, 2024

In Search of Trees: Decision-Tree Policy Synthesis for Black-Box Systems via Search
Emir Demirović, Christian Schilling, Anna Lukina
Reinforcement Learning Decision Tree Black Box Search Query Tree Specie Neural Network Policy Decision Tree Policy

July 29, 2024

Detecting Unsafe Behavior in Neural Network Imitation Policies for Caregiving Robotics
Andrii Tytarenko
Robotics Domain Based Policy Neural Network Policy Robotics Benchmark Imitation Learned Policy

June 3, 2024

Deep Reinforcement Learning Behavioral Mode Switching Using Optimal Control Based on a Latent Space Objective
Sindre Benjamin Remman, Bjørn Andreas Kristiansen, Anastasios M. Lekkas
Deep Reinforcement Learning Latent Space Optimal Control Neural Network Policy

June 2, 2024

Learning-Based Verification of Stochastic Dynamical Systems with Neural Network Policies
Thom Badings, Wietze Koops, Sebastian Junges, Nils Jansen
Reinforcement Learning Algorithm State Space Stochastic Dynamical System Neural Network Policy Reach Avoid

May 29, 2024

Causal Action Influence Aware Counterfactual Data Augmentation
Núria Armengol Urpí, Marco Bagatella, Marin Vlastelica, Georg Martius
Counterfactual Reasoning Neural Network Policy Many Trajectory Offline Training

April 5, 2024

Intervention-Assisted Policy Gradient Methods for Online Stochastic Queuing Network Optimization: Technical Report
Jerrod Wigmore, Brooke Shrader, Eytan Modiano
Deep Reinforcement Learning Policy Gradient Technical Report Neural Network Policy Deep Reinforcement Learning Based Online Stochastic Classical Control

March 21, 2024

Distilling Reinforcement Learning Policies for Interpretable Robot Locomotion: Gradient Boosting Machines and Symbolic Regression
Fernando Acero, Zhibin Li
Reinforcement Learning Symbolic Regression Gradient Boosting Robot Locomotion Policy Distillation Neural Network Policy Reinforcement Learning Policy

March 14, 2024

SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning
Nicholas Zolman, Urban Fasel, J. Nathan Kutz, Steven L. Brunton
Deep Reinforcement Learning Nonlinear Dynamic Interpretable Way Neural Network Policy Weak Sindy Interpretable Control

February 9, 2024

Deceptive Path Planning via Reinforcement Learning with Graph Neural Networks
Michael Y. Fatemi, Wesley A. Suttle, Brian M. Sadler
Reinforcement Learning Graph Neural Network Neural Network Policy Strategic Deception

December 8, 2023

Backward Learning for Goal-Conditioned Policies
Marc Höftmann, Jan Robine, Stefan Harmeling
Reinforcement Learning Imitation Learning Goal Conditioned Policy Maze Environment Neural Network Policy Backward Learning

December 3, 2023

Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees
Đorđe Žikelić, Mathias Lechner, Abhinav Verma, Krishnendu Chatterjee, Thomas A. Henzinger
Reinforcement Learning Stochastic Environment Formal Guarantee Neural Network Policy Reach Avoid Compositional Reinforcement Learning Evolving Policy Stochastic Control System

July 31, 2023

Discovering Adaptable Symbolic Algorithms from Scratch
Stephen Kelly, Daniel S. Park, Xingyou Song, Mitchell McIntire, Pranav Nashikkar, Ritam Guha, Wolfgang Banzhaf, Kalyanmoy Deb, Vishnu Naresh Boddeti, Jie Tan, Esteban Real
Zero Shot Non Humanoid Robot Autonomous Robot Scratch Project Neural Network Policy Non Stationary Reinforcement Learning

June 30, 2023

Decentralized Motor Skill Learning for Complex Robotic Systems
Yanjiang Guo, Zheyuan Jiang, Yen-Jen Wang, Jingyue Gao, Jianyu Chen
Reinforcement Learning Decentralized Learning Complex Robotic System Decentralized Control Neural Network Policy

May 22, 2023

End-to-End Stable Imitation Learning via Autonomous Neural Dynamic Policies
Dionis Totsila, Konstantinos Chatzilygeroudis, Denis Hadjivelichkov, Valerio Modugno, Ioannis Hatzilygeroudis, Dimitrios Kanoulas
End to End Control Policy Adaptive Policy Neural Network Policy Autonomous Dynamical System Conditioned Imitation

October 13, 2022

Interpreting Neural Policies with Disentangled Tree Representations
Tsun-Hsuan Wang, Wei Xiao, Tim Seyde, Ramin Hasani, Daniela Rus
Inherent Interpretability Robot Learning Disentanglement Capability Disentangled Representation Neural Dynamic Neural Network Policy Compact Neural Network

July 4, 2022

Goal-Conditioned Generators of Deep Policies
Francesco Faccio, Vincent Herrmann, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber
Goal Conditioned Reinforcement Learning Single Agent Reinforcement Learning Neural Network Policy Deep Policy Expressive Policy Conditioned Generation

July 3, 2022

Renaissance Robot: Optimal Transport Policy Fusion for Learning Diverse Skills
Julia Tan, Ransalu Senanayake, Fabio Ramos
Deep Reinforcement Learning Reward Shaping Policy Adaptation Diverse Skill Neural Network Policy Policy Synthesis Robotics Problem Da Vinci

June 14, 2022

Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising
Zikang Xiong, Joe Eappen, He Zhu, Suresh Jagannathan
Adversarial Attack Deep Reinforcement Learning Data Detection Denoising Process Adversarial Scenario Neural Network Policy

May 24, 2022

Learning Stabilizing Policies in Stochastic Control Systems
Đorđe Žikelić, Mathias Lechner, Krishnendu Chatterjee, Thomas A. Henzinger
Joint Optimization Neural Network Policy Single Learning Stochastic Control System