Model Free Deep Reinforcement Learning

Model-free deep reinforcement learning (DRL) focuses on training agents to make optimal decisions in complex environments without explicitly modeling the environment's dynamics. Current research emphasizes improving sample efficiency, often through techniques like episodic memory, uncertainty-aware reward functions, and novel exploration strategies within various model architectures such as actor-critic methods and deep Q-networks. This approach is proving valuable across diverse applications, including robotics (manipulation, navigation, control), autonomous driving, and resource management (energy systems, supply chains), by enabling the development of robust and adaptable control policies in scenarios with high dimensionality and uncertainty.

Papers

November 11, 2024

OCMDP: Observation-Constrained Markov Decision Process
Taiyi Wang, Jianheng Liu, Jiaye Li, Zhihao Wu, Yu Wu
Observable Markov Decision Process Model Free Deep Reinforcement Learning Full Observability

September 2, 2024

AI Olympics challenge with Evolutionary Soft Actor Critic
Marco Calì, Alberto Sinigaglia, Niccolò Turcato, Ruggero Carli, Gian Antonio Susto
Practical Algorithm Evolution Strategy Model Free Deep Reinforcement Learning AI City Challenge Soft Actor Critic Algorithm

May 22, 2024

Uncertainty-Aware DRL for Autonomous Vehicle Crowd Navigation in Shared Space
Mahsa Golchoubian, Moojan Ghafurian, Kerstin Dautenhahn, Nasser Lashgarian Azad
Reinforcement Learning Deep Reinforcement Learning Model Free Deep Reinforcement Learning Crowd Navigation Pedestrian Simulation Autonomous Miniature Shared Space

February 25, 2024

Harnessing the Synergy between Pushing, Grasping, and Throwing to Enhance Object Manipulation in Cluttered Scenarios
Hamidreza Kasaei, Mohammadreza Kasaei
Robotic Manipulation Functional Grasping Model Free Deep Reinforcement Learning Model Synergy Cluttered Scene UNO Push

February 4, 2024

Integrating DeepRL with Robust Low-Level Control in Robotic Manipulators for Non-Repetitive Reaching Tasks
Mehdi Heydari Shahna, Seyed Adel Alizadeh Kolagar, Jouni Mattila
Deep Reinforcement Learning Collision Avoidance Collision Free Robotic Manipulator Model Free Deep Reinforcement Learning Low Level

January 19, 2024

Episodic Reinforcement Learning with Expanded State-reward Space
Dayang Liang, Yaru Zhang, Yunlong Liu
Deep Reinforcement Learning Episodic Memory Model Free Deep Reinforcement Learning Episodic Reinforcement Learning Prompt Expansion State Reward Episodic Control

December 22, 2023

An investigation of belief-free DRL and MCTS for inspection and maintenance planning
Daniel Koutas, Elizabeth Bismut, Daniel Straub
Deep Reinforcement Learning Monte Carlo Tree Search Comprehensive Investigation Sequential Decision Belief State Visual Inspection Model Free Deep Reinforcement Learning Minimax McTs Maintenance Planning

December 16, 2023

Fractional Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing
Lyudong Jin, Ming Tang, Meng Zhang, Hao Wang
Mobile Edge Computing Model Free Deep Reinforcement Learning Neural Fractional

November 29, 2023

Deep Reinforcement Learning Graphs: Feedback Motion Planning via Neural Lyapunov Verification
Armin Ghanbarzadeh, Esmaeil Najafi
External Control Graph Reinforcement Learning Model Free Deep Reinforcement Learning Training Agent Neural Lyapunov Feedback Motion Planning Feedback Motion

November 13, 2023

Towards Transferring Tactile-based Continuous Force Control Policies from Simulation to Robot
Luca Lach, Robert Haschke, Davide Tateo, Jan Peters, Helge Ritter, Júlia Borràs, Carme Torras
Robot Person Robotics Domain Simulation Study Model Free Deep Reinforcement Learning Force Feedback Active Visuo Tactile

July 26, 2023

Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing
Max Yang, Yijiong Lin, Alex Church, John Lloyd, Dandan Zhang, David A. W. Barton, Nathan F. Lepora
Deep Reinforcement Learning Tactile Sensing Model Free Deep Reinforcement Learning Non Prehensile Manipulation Sim to Real Complex Robotic Task

July 3, 2023

Towards Safe Autonomous Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approach
Iman Sharifi, Mustafa Yildirim, Saber Fallah
Reinforcement Learning Deep Reinforcement Learning Autonomous Driving Model Free Deep Reinforcement Learning Autonomous Driving Policy

May 29, 2023

Perimeter Control Using Deep Reinforcement Learning: A Model-free Approach towards Homogeneous Flow Rate Optimization
Xiaocan Li, Ray Coden Mercurius, Ayal Taitler, Xiaoyu Wang, Mohammad Noaeen, Scott Sanner, Baher Abdulhai
Deep Reinforcement Learning Model Free Model Free Reinforcement Learning Model Free Deep Reinforcement Learning Perimeter Defense Optimal Flow

April 20, 2023

TempoRL: laser pulse temporal shape optimization with Deep Reinforcement Learning
Francesco Capuano, Davorin Peceli, Gabriele Tiboni, Raffaello Camoriano, Bedřich Rus
Deep Reinforcement Learning Model Free Deep Reinforcement Learning High Power Laser Laser Pulse

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 8, 2023

Using Memory-Based Learning to Solve Tasks with State-Action Constraints
Mrinal Verghese, Chris Atkeson
Reinforcement Learning New Task Model Free Deep Reinforcement Learning State Constraint Memory Based

February 26, 2023

Reinforcement Learning Based Pushing and Grasping Objects from Ungraspable Poses
Hao Zhang, Hongzhuo Liang, Lin Cong, Jianzhi Lyu, Long Zeng, Pingfa Feng, Jianwei Zhang
Proximal Policy Optimization Variational Method Functional Grasping Model Free Deep Reinforcement Learning Stable Pushing Grasping Object Unusual Pose

February 23, 2023

To the Noise and Back: Diffusion for Shared Autonomy
Takuma Yoneda, Luzhe Sun, and Ge Yang, Bradly Stadie, Matthew Walter
Diffusion Explainer Industrial Disturbing Noise Autonomous Agent Legal Autonomy Model Free Deep Reinforcement Learning Task Specific Reward Shared Autonomy Direct Teleoperation

January 10, 2023

Learning to Perceive in Deep Model-Free Reinforcement Learning
Gonçalo Querido, Alberto Sardinha, Francisco S. Melo
LeArning Abstract Model Free Deep Reinforcement Learning Active Perception Hard Attention Recurrent Attention

December 27, 2022

Optimal scheduling of island integrated energy systems considering multi-uncertainties and hydrothermal simultaneous transmission: A deep reinforcement learning approach
Yang Li, Fanjin Bu, Yuanzheng Li, Chao Long
Deep Reinforcement Learning Deep Reinforcement Learning Approach Model Free Deep Reinforcement Learning Energy System Optimal Scheduling Concurrent Transmission Scheduling Framework

Model Free Deep Reinforcement Learning

Papers

OCMDP: Observation-Constrained Markov Decision Process

AI Olympics challenge with Evolutionary Soft Actor Critic

Uncertainty-Aware DRL for Autonomous Vehicle Crowd Navigation in Shared Space

Harnessing the Synergy between Pushing, Grasping, and Throwing to Enhance Object Manipulation in Cluttered Scenarios

Integrating DeepRL with Robust Low-Level Control in Robotic Manipulators for Non-Repetitive Reaching Tasks

Episodic Reinforcement Learning with Expanded State-reward Space

An investigation of belief-free DRL and MCTS for inspection and maintenance planning

Fractional Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing

Deep Reinforcement Learning Graphs: Feedback Motion Planning via Neural Lyapunov Verification

Towards Transferring Tactile-based Continuous Force Control Policies from Simulation to Robot

Sim-to-Real Model-Based and Model-Free Deep Reinforcement Learning for Tactile Pushing

Towards Safe Autonomous Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approach

Perimeter Control Using Deep Reinforcement Learning: A Model-free Approach towards Homogeneous Flow Rate Optimization

TempoRL: laser pulse temporal shape optimization with Deep Reinforcement Learning

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

Using Memory-Based Learning to Solve Tasks with State-Action Constraints

Reinforcement Learning Based Pushing and Grasping Objects from Ungraspable Poses

To the Noise and Back: Diffusion for Shared Autonomy

Learning to Perceive in Deep Model-Free Reinforcement Learning

Optimal scheduling of island integrated energy systems considering multi-uncertainties and hydrothermal simultaneous transmission: A deep reinforcement learning approach