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

March 7, 2023

Sample-efficient Real-time Planning with Curiosity Cross-Entropy Method and Contrastive Learning
Mostafa Kotb, Cornelius Weber, Stefan Wermter
Contrastive Learning Real Time Model Based Reinforcement Learning Model Free Reinforcement Learning Cross Entropy Intrinsic Reward Sampling Based Curiosity Inducing Situation

March 3, 2023

Approximating Energy Market Clearing and Bidding With Model-Based Reinforcement Learning
Thomas Wolgast, Astrid Nieße
Reinforcement Learning Multi Agent Reinforcement Learning Model Based Reinforcement Learning Paper Bidding Energy Market Market Clearing

March 1, 2023

The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms
Anirudh Vemula, Yuda Song, Aarti Singh, J. Andrew Bagnell, Sanjiban Choudhury
Practical Algorithm Model Based Reinforcement Learning Learned Model Regret Algorithm Lazy Search

February 24, 2023

Model-Based Uncertainty in Value Functions
Carlos E. Luis, Alessandro G. Bottero, Julia Vinogradska, Felix Berkenkamp, Jan Peters
Model Based Reinforcement Learning Value Function Uncertainty Modeling Bellman Equation Reinforcement Learning Architecture Inefficient Exploration

February 20, 2023

Understanding the effect of varying amounts of replay per step
Animesh Kumar Paul, Videh Raj Nema
Mixed Effect Model Based Reinforcement Learning Model Free Deep Q Network Experience Replay Sample STEP Quantity Aware RePLAy Loss Model Free Algorithm

February 9, 2023

Equivariant MuZero
Andreea Deac, Théophane Weber, George Papamakarios
Deep Reinforcement Learning Model Based Reinforcement Learning Inter Part Equivariance Equivariant Map

February 8, 2023

Predictable MDP Abstraction for Unsupervised Model-Based RL
Seohong Park, Sergey Levine
Model Based Reinforcement Learning Unsupervised Setting Unsupervised Reinforcement Learning Model Based Planning

February 2, 2023

Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function
Ruijie Zheng, Xiyao Wang, Huazhe Xu, Furong Huang
Model Based Reinforcement Learning Model Ensemble Single Model Bellman Operator Lipschitz Regularization

January 30, 2023

Learning Control from Raw Position Measurements
Fabio Amadio, Alberto Dalla Libera, Daniel Nikovski, Ruggero Carli, Diego Romeres
Policy Gradient Learning Based Model Based Reinforcement Learning Physical System Location Data

January 28, 2023

STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning
Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel, Mengdi Wang, Furong Huang, Dinesh Manocha
Reinforcement Learning Model Based Reinforcement Learning Steering Technique Bayesian Regret Directed Exploration Incentivized Exploration

January 24, 2023

January 20, 2023

Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning
Zifan Wu, Chao Yu, Chen Chen, Jianye Hao, Hankz Hankui Zhuo
Model Based Reinforcement Learning Policy Learning Predictive Uncertainty High Level Plan Model Learning Stable Learning

January 9, 2023

Exploration in Model-based Reinforcement Learning with Randomized Reward
Lingxiao Wang, Ping Li
Environment Exploration Model Based Reinforcement Learning Optimal Regret Stochastic Reward

December 30, 2022

Pontryagin Optimal Control via Neural Networks
Chengyang Gu, Hui Xiong, Yize Chen
Neural Network High Dimensional Model Based Reinforcement Learning

December 27, 2022

Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation
Taehyun Hwang, Min-hwan Oh
Model Based Reinforcement Learning Efficient Reinforcement Learning Episodic Markov Decision Process Multinomial Logistic Linear Markov Decision Process

December 17, 2022

Latent Variable Representation for Reinforcement Learning
Tongzheng Ren, Chenjun Xiao, Tianjun Zhang, Na Li, Zhaoran Wang, Sujay Sanghavi, Dale Schuurmans, Bo Dai
Reinforcement Learning Model Based Reinforcement Learning Latent Variable Latent Variable Model Variable Model

December 16, 2022

A Simple Decentralized Cross-Entropy Method
Zichen Zhang, Jun Jin, Martin Jagersand, Jun Luo, Dale Schuurmans
Model Based Reinforcement Learning Cross Entropy Decentralized FL Centralized Model

December 5, 2022

Physics-Informed Model-Based Reinforcement Learning
Adithya Ramesh, Balaraman Ravindran
Reinforcement Learning Model Based Reinforcement Learning

November 4, 2022

The Benefits of Model-Based Generalization in Reinforcement Learning
Kenny Young, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber
Reinforcement Learning Model Based Reinforcement Learning Complementary Benefit Model Generalization Experience Replay Model Learning Learned Model