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

November 3, 2022

Contrastive Value Learning: Implicit Models for Simple Offline RL
Bogdan Mazoure, Benjamin Eysenbach, Ofir Nachum, Jonathan Tompson
Offline Reinforcement Learning Reward Function Model Based Reinforcement Learning Implicit Model Step to Step Dynamic Contrastive Reward

November 2, 2022

Model-based Reinforcement Learning with a Hamiltonian Canonical ODE Network
Yao Feng, Yuhong Jiang, Hang Su, Dong Yan, Jun Zhu
Model Based Reinforcement Learning Complex Dynamic Hamiltonian System Novel Model Hamiltonian Function

October 27, 2022

SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering
Jun Lv, Yunhai Feng, Cheng Zhang, Shuang Zhao, Lin Shao, Cewu Lu
Model Based Reinforcement Learning Model Free Differentiable Physic Elev Vision Sam Active Sensing

October 23, 2022

Active Exploration for Robotic Manipulation
Tim Schneider, Boris Belousov, Georgia Chalvatzaki, Diego Romeres, Devesh K. Jha, Jan Peters
Robotic Manipulation Model Based Reinforcement Learning Active Exploration Sparse Reward Environment

October 21, 2022

E-MCTS: Deep Exploration in Model-Based Reinforcement Learning by Planning with Epistemic Uncertainty
Yaniv Oren, Matthijs T. J. Spaan, Wendelin Böhmer
Model Based Reinforcement Learning Monte Carlo Tree Search Epistemic Uncertainty

October 19, 2022

On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning
Yifan Xu, Nicklas Hansen, Zirui Wang, Yung-Chieh Chan, Hao Su, Zhuowen Tu
Reinforcement Learning Model Based Reinforcement Learning Task Feasibility Task Transfer Multi Task Fine Tuning

October 17, 2022

On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning
Philipp Becker, Gerhard Neumann
High Uncertainty Anticipation State Space Model Model Based Reinforcement Learning Deep State Space Model Recurrent State Space Model

October 4, 2022

DISCOVER: Deep identification of symbolically concise open-form PDEs via enhanced reinforcement-learning
Mengge Du, Yuntian Chen, Dongxiao Zhang
Reinforcement Learning Deep Learning Deep Reinforcement Learning Model Based Reinforcement Learning

September 29, 2022

Learning Parsimonious Dynamics for Generalization in Reinforcement Learning
Tankred Saanum, Eric Schulz
Reinforcement Learning Strong Generalization Model Based Reinforcement Learning Latent Variable Policy Learning Latent Dynamic Parsimonious Machine Learning

September 20, 2022

A Spiking Neural Network Learning Markov Chain
Mikhail Kiselev
Model Based Reinforcement Learning Transition Probability World Dynamic

September 16, 2022

September 12, 2022

Model-based Reinforcement Learning with Multi-step Plan Value Estimation
Haoxin Lin, Yihao Sun, Jiaji Zhang, Yang Yu
Reinforcement Learning Learning Based Model Based Reinforcement Learning

September 7, 2022

Concept-modulated model-based offline reinforcement learning for rapid generalization
Nicholas A. Ketz, Praveen K. Pilly
Zero Shot Model Based Reinforcement Learning Model Based Offline Reinforcement Learning Provable Generalization

September 4, 2022

Variational Inference for Model-Free and Model-Based Reinforcement Learning
Felix Leibfried
Reinforcement Learning Bayesian Optimization Variational Inference Model Based Reinforcement Learning Model Free Approximate Bayesian Inference

August 30, 2022

August 3, 2022

Bayesian regularization of empirical MDPs
Samarth Gupta, Daniel N. Hill, Lexing Ying, Inderjit Dhillon
Markov Decision Process Optimal Policy Model Based Reinforcement Learning Robust Policy Entropy Regularization Bayesian Regularization MDP Model

July 28, 2022

Raising Student Completion Rates with Adaptive Curriculum and Contextual Bandits
Robert Belfer, Ekaterina Kochmar, Iulian Vlad Serban
Model Based Reinforcement Learning Contextual Bandit Intelligent Tutoring System Personalization Performance Student Engagement Adaptive Curriculum

July 25, 2022

Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy
Xiyao Wang, Wichayaporn Wongkamjan, Furong Huang
Model Based Reinforcement Learning Policy Learning Learning Dynamic Temporal Moment Learned Dynamic Mixture Policy Evolving Policy

Model Based Reinforcement Learning

Papers

Contrastive Value Learning: Implicit Models for Simple Offline RL

Model-based Reinforcement Learning with a Hamiltonian Canonical ODE Network

SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering

Active Exploration for Robotic Manipulation

E-MCTS: Deep Exploration in Model-Based Reinforcement Learning by Planning with Epistemic Uncertainty

On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning

On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning

DISCOVER: Deep identification of symbolically concise open-form PDEs via enhanced reinforcement-learning

Learning Parsimonious Dynamics for Generalization in Reinforcement Learning

A Spiking Neural Network Learning Markov Chain

Value Summation: A Novel Scoring Function for MPC-based Model-based Reinforcement Learning

Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning

Model-based Reinforcement Learning with Multi-step Plan Value Estimation

Concept-modulated model-based offline reinforcement learning for rapid generalization

Variational Inference for Model-Free and Model-Based Reinforcement Learning

Model-Based Reinforcement Learning with SINDy

An Analysis of Model-Based Reinforcement Learning From Abstracted Observations

Bayesian regularization of empirical MDPs

Raising Student Completion Rates with Adaptive Curriculum and Contextual Bandits

Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy