Model Free

Model-free methods in machine learning and control aim to learn optimal strategies or models without relying on explicit knowledge of the underlying system dynamics. Current research focuses on developing efficient model-free algorithms for reinforcement learning, including those employing neural networks, normalizing flows, and advanced optimization techniques like damped Newton methods, to address challenges in various domains such as robotics, process control, and anomaly detection. These approaches are significant because they offer greater flexibility and robustness compared to model-based methods, particularly when dealing with complex or unknown systems, leading to improved performance and reduced computational costs in diverse applications.

Papers

April 11, 2023

Real-Time Model-Free Deep Reinforcement Learning for Force Control of a Series Elastic Actuator
Ruturaj Sambhus, Aydin Gokce, Stephen Welch, Connor W. Herron, Alexander Leonessa
Model Free Force Control Model Free Deep Reinforcement Learning Series Elastic Actuator Force Trajectory

March 6, 2023

3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction
Jiaqi Guan, Wesley Wei Qian, Xingang Peng, Yufeng Su, Jian Peng, Jianzhu Ma
Molecule Generation Model Free Drug Design Affinity Prediction Protein Target Equivariant Diffusion

February 28, 2023

Model-Free and Learning-Free Proprioceptive Humanoid Movement Control
Boren Jiang, Ximeng Tao, Yuanfeng Han, Wanze Li, Gregory S. Chirikjian
Model Free Robot Motion Proprioceptive Sensing Robot Design Next Active Object Humanoid Control

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

January 24, 2023

PowerQuant: Automorphism Search for Non-Uniform Quantization
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly
Deep Neural Network Model Free Multiplier Free Quantization Non Uniform Quantization

January 18, 2023

OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models
Xingyi He, Jiaming Sun, Yuang Wang, Di Huang, Hujun Bao, Xiaowei Zhou
Model Free Feature Matching Object Pose Estimation Detector Free Parallel SfM Pose Estimation Pipeline

December 17, 2022

Comparison of Model-Free and Model-Based Learning-Informed Planning for PointGoal Navigation
Yimeng Li, Arnab Debnath, Gregory J. Stein, Jana Kosecka
Consistent Comparison Learning Based Model Free Navigation Task Observable Markov Decision Process Reinforcement Learning Approach

December 13, 2022

Model-Free Approach to Fair Solar PV Curtailment Using Reinforcement Learning
Zhuo Wei, Frits de Nijs, Jinhao Li, Hao Wang
Reinforcement Learning Model Free Power Flow

November 28, 2022

Provably Efficient Model-free RL in Leader-Follower MDP with Linear Function Approximation
Arnob Ghosh
High Efficiency Bandit Feedback Model Free Markov Game Single Agent Linear Function Approximation Linear MDPs

November 21, 2022

A Novel Uncalibrated Visual Servoing Controller Baesd on Model-Free Adaptive Control Method with Neural Network
Haibin Zeng, Yueyong Lyu, Jiaming Qi, Shuangquan Zou, Tanghao Qin, Wenyu Qin
Neural Network Robotic Arm Model Free Visual Servoing

November 15, 2022

Model free variable importance for high dimensional data
Naofumi Hama, Masayoshi Mase, Art B. Owen
Full Model Value Function High Dimensional Data Model Free Free Energy Variable Importance Shapley Method

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 20, 2022

Safe Policy Improvement in Constrained Markov Decision Processes
Luigi Berducci, Radu Grosu
Reinforcement Learning Model Free Reward Shaping Constrained Markov Decision Process Policy Improvement Scalar Reward

October 14, 2022

Model-Free Characterizations of the Hamilton-Jacobi-Bellman Equation and Convex Q-Learning in Continuous Time
Fan Lu, Joel Mathias, Sean Meyn, Karanjit Kalsi
Reinforcement Learning Model Free Continuous Time Finite Horizon Q Function Hamilton Jacobi Bellman Convex Q Learning

September 15, 2022

Learning to Exploit Elastic Actuators for Quadruped Locomotion
Antonin Raffin, Daniel Seidel, Jens Kober, Alin Albu-Schäffer, João Silvério, Freek Stulp
LeArning Abstract Model Free Legged Locomotion Efficient Locomotion Quadruped Locomotion Elastic Actuator Rolling Locomotion Ability

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 24, 2022

A model-based approach to meta-Reinforcement Learning: Transformers and tree search
Brieuc Pinon, Jean-Charles Delvenne, Raphaël Jungers
Transformer Megatron Decepticons Meta Learning Model Based Model Free Meta Reinforcement Learning Tree Search Meta Rl Algorithm

July 4, 2022

Model-Free 3D Shape Control of Deformable Objects Using Novel Features Based on Modal Analysis
Bohan Yang, Bo Lu, Wei Chen, Fangxun Zhong, Yun-Hui Liu
Deformable Object Model Free Shape Control Modal Analysis New Feature Deformation Control

June 24, 2022

Data-driven reduced order models using invariant foliations, manifolds and autoencoders
Robert Szalai
Supervised Autoencoder Data Driven Closed Loop Model Free Class Manifold Order Model Invariant Manifold

June 8, 2022

ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret
Stephen McAleer, Gabriele Farina, Marc Lanctot, Tuomas Sandholm
Nash Equilibrium Value Function Video Game Model Free Importance Sampling Digital Computing Approximate Nash Equilibrium Counterfactual Regret Minimization Static Regret Fictitious Self Play

Model Free

Papers

Real-Time Model-Free Deep Reinforcement Learning for Force Control of a Series Elastic Actuator

3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction

Model-Free and Learning-Free Proprioceptive Humanoid Movement Control

Understanding the effect of varying amounts of replay per step

PowerQuant: Automorphism Search for Non-Uniform Quantization

OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models

Comparison of Model-Free and Model-Based Learning-Informed Planning for PointGoal Navigation

Model-Free Approach to Fair Solar PV Curtailment Using Reinforcement Learning

Provably Efficient Model-free RL in Leader-Follower MDP with Linear Function Approximation

A Novel Uncalibrated Visual Servoing Controller Baesd on Model-Free Adaptive Control Method with Neural Network

Model free variable importance for high dimensional data

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

Safe Policy Improvement in Constrained Markov Decision Processes

Model-Free Characterizations of the Hamilton-Jacobi-Bellman Equation and Convex Q-Learning in Continuous Time

Learning to Exploit Elastic Actuators for Quadruped Locomotion

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

A model-based approach to meta-Reinforcement Learning: Transformers and tree search

Model-Free 3D Shape Control of Deformable Objects Using Novel Features Based on Modal Analysis

Data-driven reduced order models using invariant foliations, manifolds and autoencoders

ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret