Policy Model

Policy models are computational representations of decision-making strategies, aiming to optimize outcomes in diverse applications, from robotics and epidemic control to language model training. Current research emphasizes improving policy robustness and adaptability through techniques like multi-policy collaboration (combining blind and perceptive policies), adversarial and contrastive learning to refine model outputs against human-like preferences, and incorporating interpretable concepts for better understanding and control. These advancements are crucial for enhancing the performance and reliability of autonomous systems and improving the design of effective interventions in complex real-world scenarios.

Papers

November 15, 2024

Brain-inspired Action Generation with Spiking Transformer Diffusion Policy Model
Qianhao Wang, Yinqian Sun, Enmeng Lu, Qian Zhang, Yi Zeng
Spiking Neural Network Denoising Diffusion Probabilistic Model Brain Inspired Action Generation Spiking Transformer Policy Model Spiking Diffusion

September 24, 2024

MBC: Multi-Brain Collaborative Control for Quadruped Robots
Hang Liu, Yi Cheng, Rankun Li, Xiaowen Hu, Linqi Ye, Houde Liu
Multi Agent Reinforcement Learning Quadruped Robot Robot Performance Locomotion Control Policy Model

June 12, 2024

It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF
Taiming Lu, Lingfeng Shen, Xinyu Yang, Weiting Tan, Beidi Chen, Huaxiu Yao
Reinforcement Learning Human Feedback Reward Model Reinforcement Learning From Human Feedback Reward Report Training Model Model Augmentation Policy Model

May 27, 2024

Finding good policies in average-reward Markov Decision Processes without prior knowledge
Adrienne Tuynman, Rémy Degenne, Emilie Kaufmann
Sample Complexity Optimal Policy Prior Knowledge Average Reward Markov Decision Process High Performing Policy Policy Model Policy Identification

March 16, 2024

Game and Reference: Policy Combination Synthesis for Epidemic Prevention and Control
Zhiyi Tan, Bingkun Bao
External Control Game Content Higher Quality Reference Pandemic Control Policy Synthesis Sub Optimal Policy Policy Model Epidemic Decision

January 30, 2024

Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests
Brielen Madureira, David Schlangen
Instruction Following Action Feature Auxiliary Task Meta Level Clarification Question Instruction Augmentation Policy Model

February 23, 2023

Concept Learning for Interpretable Multi-Agent Reinforcement Learning
Renos Zabounidis, Joseph Campbell, Simon Stepputtis, Dana Hughes, Katia Sycara
Neural Network Multi Agent Reinforcement Learning Multi Agent Concept Learning Multi Agent Robotic System Policy Model

December 15, 2022

Neural Network Augmented Compartmental Pandemic Models
Lorenz Kummer, Kevin Sidak
Mathematical Model Epidemic Forecasting Compartmental Model Policy Model Susceptible Infected

December 6, 2022

Learning Locally, Communicating Globally: Reinforcement Learning of Multi-robot Task Allocation for Cooperative Transport
Kazuki Shibata, Tomohiko Jimbo, Tadashi Odashima, Keisuke Takeshita, Takamitsu Matsubara
Reinforcement Learning LeArning Abstract Multi Agent Reinforcement Learning Multi Robot System Timely Communication Multi Robot Task Cooperative Transportation Object Transportation Policy Model

June 1, 2022

Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL
Siyi Hu, Chuanlong Xie, Xiaodan Liang, Xiaojun Chang
Long Term Cooperation Cooperative Multi Agent Reinforcement Learning Multi Agent Challenge Multi Agent Cooperation Multi Agent Task Multi Agent Particle Multi Agent RL Policy Model Challenging Role Type

Policy Model

Papers

Brain-inspired Action Generation with Spiking Transformer Diffusion Policy Model

MBC: Multi-Brain Collaborative Control for Quadruped Robots

It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF

Finding good policies in average-reward Markov Decision Processes without prior knowledge

Game and Reference: Policy Combination Synthesis for Epidemic Prevention and Control

Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests

Concept Learning for Interpretable Multi-Agent Reinforcement Learning

Neural Network Augmented Compartmental Pandemic Models

Learning Locally, Communicating Globally: Reinforcement Learning of Multi-robot Task Allocation for Cooperative Transport

Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL