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

July 25, 2022

Adaptive Asynchronous Control Using Meta-learned Neural Ordinary Differential Equations
Achkan Salehi, Steffen Rühl, Stephane Doncieux
Real World Model Based Reinforcement Learning Neural Ordinary Differential Equation Robot Simulation Adaptive Model Continuous Prediction

July 15, 2022

Skill-based Model-based Reinforcement Learning
Lucy Xiaoyang Shi, Joseph J. Lim, Youngwoon Lee
Model Based Reinforcement Learning Parameterized Skill Skill Based Reinforcement Learning

June 29, 2022

Provably Efficient Reinforcement Learning for Online Adaptive Influence Maximization
Kaixuan Huang, Yu Wu, Xuezhou Zhang, Shenyinying Tu, Qingyun Wu, Mengdi Wang, Huazheng Wang
Optimal Policy Model Based Reinforcement Learning Influence Maximization

June 28, 2022

Masked World Models for Visual Control
Younggyo Seo, Danijar Hafner, Hao Liu, Fangchen Liu, Stephen James, Kimin Lee, Pieter Abbeel
Vision Transformer Model Based Reinforcement Learning Vision Task World Model Visual Control Visual Robotic Manipulation Visual Model Based

June 27, 2022

Causal Dynamics Learning for Task-Independent State Abstraction
Zizhao Wang, Xuesu Xiao, Zifan Xu, Yuke Zhu, Peter Stone
Model Based Reinforcement Learning Learned Dynamic State Abstraction Causal System Causal Dynamic Learning

June 19, 2022

A Survey on Model-based Reinforcement Learning
Fan-Ming Luo, Tian Xu, Hang Lai, Xiong-Hui Chen, Weinan Zhang, Yang Yu
Reinforcement Learning Timely Survey Multi Agent Reinforcement Learning Model Based Reinforcement Learning Goal Conditioned Reinforcement Learning Model Learning

June 16, 2022

Understanding Decision-Time vs. Background Planning in Model-Based Reinforcement Learning
Safa Alver, Doina Precup
Model Based Reinforcement Learning Dynamic Programming Learned Model Decision Time Planning Planning Approach

June 9, 2022

A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning
Jixian Guo, Mingming Gong, Dacheng Tao
Model Based Reinforcement Learning Relational Model Dynamic Prediction Hidden Dynamic

June 8, 2022

Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games
Yuling Yan, Gen Li, Yuxin Chen, Jianqing Fan
Model Based Reinforcement Learning Nash Equilibrium Markov Game Minimax Optimality Infinite Horizon Approximate Nash Equilibrium

June 6, 2022

June 4, 2022

June 2, 2022

Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning
Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel, Brian M. Sadler, Furong Huang, Pratap Tokekar, Dinesh Manocha
Reinforcement Learning Model Based Reinforcement Learning Sublinear Regret State Action Pair Stein Discrepancy

May 30, 2022

Stock Trading Optimization through Model-based Reinforcement Learning with Resistance Support Relative Strength
Huifang Huang, Ting Gao, Yi Gui, Jin Guo, Peng Zhang
Reinforcement Learning Model Based Reinforcement Learning Reinforcement Learning Algorithm Quantitative Finance Trading Strategy Effective Resistance

May 28, 2022

Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning
Remo Sasso, Matthia Sabatelli, Marco A. Wiering
Reinforcement Learning Model Based Reinforcement Learning Multi Source Knowledge Extraction State Action Space

May 25, 2022

Scalable Multi-Agent Model-Based Reinforcement Learning
Vladimir Egorov, Aleksei Shpilman
Multi Agent Reinforcement Learning Model Based Reinforcement Learning Centralized Training

Model Based Reinforcement Learning

Papers

Adaptive Asynchronous Control Using Meta-learned Neural Ordinary Differential Equations

Skill-based Model-based Reinforcement Learning

Provably Efficient Reinforcement Learning for Online Adaptive Influence Maximization

Masked World Models for Visual Control

Causal Dynamics Learning for Task-Independent State Abstraction

Using cognitive psychology to understand GPT-3

Incorporating Voice Instructions in Model-Based Reinforcement Learning for Self-Driving Cars

Model-Based Imitation Learning Using Entropy Regularization of Model and Policy

A Survey on Model-based Reinforcement Learning

Understanding Decision-Time vs. Background Planning in Model-Based Reinforcement Learning

A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning

Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games

Goal-Space Planning with Subgoal Models

Adaptive Rollout Length for Model-Based RL Using Model-Free Deep RL

Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning

Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning

Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning

Stock Trading Optimization through Model-based Reinforcement Learning with Resistance Support Relative Strength

Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning

Scalable Multi-Agent Model-Based Reinforcement Learning