Model Based Reinforcement Learning

Model-based reinforcement learning (MBRL) aims to improve the sample efficiency and robustness of reinforcement learning agents by learning a model of the environment's dynamics. Current research focuses on enhancing model accuracy and robustness through techniques like incorporating expert knowledge, using bisimulation metrics for state representation, and employing adversarial training to handle uncertainties. These advancements are leading to more efficient and reliable control policies in various applications, including robotics, autonomous driving, and even protein design, by reducing the need for extensive real-world interactions during training.

Papers

May 20, 2024

Efficient Multi-agent Reinforcement Learning by Planning
Qihan Liu, Jianing Ye, Xiaoteng Ma, Jun Yang, Bin Liang, Chongjie Zhang
Multi Agent Reinforcement Learning Multi Agent System Model Based Reinforcement Learning

May 14, 2024

Vector Field-Guided Learning Predictive Control for Motion Planning of Mobile Robots with Uncertain Dynamics
Yang Lu, Weijia Yao, Yongqian Xiao, Xinglong Zhang, Xin Xu, Yaonan Wang, Dingbang Xiao
Motion Planning Predictive Control Mobile Robot Model Based Reinforcement Learning X Vector Unknown Dynamic Mission Related Maneuverability Analysis

May 10, 2024

Learning Latent Dynamic Robust Representations for World Models
Ruixiang Sun, Hongyu Zang, Xin Li, Riashat Islam
Latent Representation Model Based Reinforcement Learning World Model Robust Representation Based Policy High Quality Distractors

May 3, 2024

Model-based reinforcement learning for protein backbone design
Frederic Renard, Cyprien Courtot, Alfredo Reichlin, Oliver Bent
Model Based Reinforcement Learning Protein Design Protein Backbone

April 29, 2024

Point Cloud Models Improve Visual Robustness in Robotic Learners
Skand Peri, Iain Lee, Chanho Kim, Li Fuxin, Tucker Hermans, Stefan Lee
Point Cloud Model Based Reinforcement Learning Learning Robot Visual Policy

April 15, 2024

A Note on Loss Functions and Error Compounding in Model-based Reinforcement Learning
Nan Jiang
Loss Function Model Based Reinforcement Learning Short Note Deep RL Stochastic Environment

April 13, 2024

Active Learning for Control-Oriented Identification of Nonlinear Systems
Bruce D. Lee, Ingvar Ziemann, George J. Pappas, Nikolai Matni
Active Learning Model Based Reinforcement Learning Nonlinear Dynamic Control Synthesis Effective Model

April 3, 2024

Model-based Reinforcement Learning for Parameterized Action Spaces
Renhao Zhang, Haotian Fu, Yilin Miao, George Konidaris
Model Based Reinforcement Learning Dynamic Learning Model Predictive Path Integral Control Action Pair

March 27, 2024

Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards
Yasin Sonmez, Neelay Junnarkar, Murat Arcak
Reinforcement Learning Model Based Reinforcement Learning Approximate Symmetry Dynamic Model Cyclic Symmetry Symmetry Breaking Perverse Incentive

March 23, 2024

Deep Gaussian Covariance Network with Trajectory Sampling for Data-Efficient Policy Search
Can Bogoclu, Robert Vosshall, Kevin Cremanns, Dirk Roos
Model Based Reinforcement Learning World Model Uncertainty Aware Trajectory Sampling Covariance Neural Network

March 21, 2024

Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control
Minjun Sung, Sambhu H. Karumanchi, Aditya Gahlawat, Naira Hovakimyan
Model Based Reinforcement Learning Robust Reinforcement Learning Adaptive Control Control Affine

March 3, 2024

Deep Incremental Model Based Reinforcement Learning: A One-Step Lookback Approach for Continuous Robotics Control
Cong Li
Reinforcement Learning Model Based Reinforcement Learning Continuous Control Task Model Evolution Model Based Deep Reinforcement Learning Robot Evolution

February 29, 2024

February 26, 2024

Model-based deep reinforcement learning for accelerated learning from flow simulations
Andre Weiner, Janis Geise
Reinforcement Learning Deep Reinforcement Learning Model Based Reinforcement Learning Flow Control Flow Simulation Model Based Deep Reinforcement Learning

February 19, 2024

The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning
Anya Sims, Cong Lu, Jakob Foerster, Yee Whye Teh
Offline Reinforcement Learning Model Based Reinforcement Learning Online Reinforcement Learning Action Free Offline Learned Dynamic Value Learning

February 14, 2024

Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption
Chenlu Ye, Jiafan He, Quanquan Gu, Tong Zhang
Model Based Reinforcement Learning Robust Reinforcement Learning Adversarial Corruption

February 13, 2024

A Distributional Analogue to the Successor Representation
Harley Wiltzer, Jesse Farebrother, Arthur Gretton, Yunhao Tang, André Barreto, Will Dabney, Marc G. Bellemare, Mark Rowland
Model Based Reinforcement Learning Distributional Reinforcement Learning Distributional Learning Successor Representation

February 5, 2024

Model Based Reinforcement Learning

Papers

Efficient Multi-agent Reinforcement Learning by Planning

Vector Field-Guided Learning Predictive Control for Motion Planning of Mobile Robots with Uncertain Dynamics

Learning Latent Dynamic Robust Representations for World Models

Model-based reinforcement learning for protein backbone design

Point Cloud Models Improve Visual Robustness in Robotic Learners

A Note on Loss Functions and Error Compounding in Model-based Reinforcement Learning

Active Learning for Control-Oriented Identification of Nonlinear Systems

Model-based Reinforcement Learning for Parameterized Action Spaces

Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards

Deep Gaussian Covariance Network with Trajectory Sampling for Data-Efficient Policy Search

Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control

Deep Incremental Model Based Reinforcement Learning: A One-Step Lookback Approach for Continuous Robotics Control

Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control

Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming

Model-based deep reinforcement learning for accelerated learning from flow simulations

The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning

Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption

A Distributional Analogue to the Successor Representation

A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning

Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning