Deep RL

Deep reinforcement learning (Deep RL) aims to train agents to make optimal decisions in complex environments by learning from experience, primarily through trial and error. Current research emphasizes improving sample efficiency, addressing challenges like value overestimation and hyperparameter sensitivity, and enhancing the interpretability and robustness of learned policies across diverse domains. Prominent algorithms include actor-critic methods (e.g., A2C, PPO, SAC, TD3, DDPG), and research explores architectures like Mixture-of-Experts networks and the integration of symbolic reasoning and program synthesis for improved generalization and long-horizon task solving. These advancements hold significant potential for applications in robotics, finance, autonomous driving, and other fields requiring adaptive decision-making in dynamic environments.

Papers

January 3, 2024

On Time-Indexing as Inductive Bias in Deep RL for Sequential Manipulation Tasks
M. Nomaan Qureshi, Ben Eisner, David Held
Deep Reinforcement Learning Inductive Bias Manipulation Task Skill Learning Deep RL Sequential Manipulation Policy Learning Method Policy Architecture

November 27, 2023

Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines
Yu-An Lin, Chen-Tao Lee, Guan-Ting Liu, Pu-Jen Cheng, Shao-Hua Sun
Reinforcement Learning Deep Reinforcement Learning Program Synthesis Long Horizon Task Deep RL State Machine Programmatic Reinforcement Learning Programmatic Policy

November 19, 2023

Robust Network Slicing: Multi-Agent Policies, Adversarial Attacks, and Defensive Strategies
Feng Wang, M. Cenk Gursoy, Senem Velipasalar
Adversarial Attack Multi Agent Deep Reinforcement Learning Deep RL Network Slicing Multi Agent Policy Defense Strategy

November 3, 2023

Towards model-free RL algorithms that scale well with unstructured data
Joseph Modayil, Zaheer Abbas
Reinforcement Learning Reward Function Reinforcement Learning Algorithm Unstructured Data Model Free Reinforcement Learning Deep RL Single Agent Reinforcement Learning

October 20, 2023

Enhanced Low-Dimensional Sensing Mapless Navigation of Terrestrial Mobile Robots Using Double Deep Reinforcement Learning Techniques
Linda Dotto de Moraes, Victor Augusto Kich, Alisson Henrique Kolling, Jair Augusto Bottega, Ricardo Bedin Grando, Anselmo Rafael Cukla, Daniel Fernando Tello Gamarra
Deep Reinforcement Learning Deep Q Network Deep RL Mobile Ground Terrestrial Mobile Robot

October 10, 2023

Zero-Shot Transfer in Imitation Learning
Alvaro Cauderan, Gauthier Boeshertz, Florian Schwarb, Calvin Zhang
Adversarial Training Imitation Learning Robot Learning Formality Transfer Disentangled Representation Deep RL Expert Level Performance

September 27, 2023

Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games
Kuo-Hao Ho, Ping-Chun Hsieh, Chiu-Chou Lin, You-Ren Luo, Feng-Jian Wang, I-Chen Wu
Reinforcement Learning 3D Content Policy OpTimization Deep Reinforcement Deep RL Human Like RL Agent Welfare

September 26, 2023

Gray-box Adversarial Attack of Deep Reinforcement Learning-based Trading Agents
Foozhan Ataiefard, Hadi Hemmati
Deep Reinforcement Learning Native Robustness Deep Reinforcement Robust Reinforcement Learning Deep RL Adversary Agent Gray Box

September 25, 2023

An AI Chatbot for Explaining Deep Reinforcement Learning Decisions of Service-oriented Systems
Andreas Metzger, Jone Bartel, Jan Laufer
Deep Learning Deep Reinforcement Learning Natural Language Explanation Deep RL AI Based Chatbot

September 22, 2023

Learning Actions and Control of Focus of Attention with a Log-Polar-like Sensor
Robin Göransson, Volker Krueger
Reinforcement Learning External Control Human Attention Human Driving Focus Deep RL Autonomous Mobile Robot Action Learning Gaze Control Cartesian Pose

August 18, 2023

DoCRL: Double Critic Deep Reinforcement Learning for Mapless Navigation of a Hybrid Aerial Underwater Vehicle with Medium Transition
Ricardo B. Grando, Junior C. de Jesus, Victor A. Kich, Alisson H. Kolling, Rodrigo S. Guerra, Paulo L. J. Drews-Jr
Deep Reinforcement Learning Actor Critic Algorithm Deep RL Mapless Navigation Late Time Transition Aerial Underwater Vehicle

June 30, 2023

Resetting the Optimizer in Deep RL: An Empirical Study
Kavosh Asadi, Rasool Fakoor, Shoham Sabach
Deep Reinforcement Learning Stochastic Gradient Descent Empirical Study Deep RL Superior Optimizer Optimization Landscape Optimal Value Function

June 19, 2023

AdaStop: adaptive statistical testing for sound comparisons of Deep RL agents
Timothée Mathieu, Riccardo Della Vecchia, Alena Shilova, Matheus Medeiros Centa, Hector Kohler, Odalric-Ambrym Maillard, Philippe Preux
Research Reproducibility Deep RL Deep Reinforcement Learning Agent Adaptive Testing

May 29, 2023

Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration
Zhihan Liu, Miao Lu, Wei Xiong, Han Zhong, Hao Hu, Shenao Zhang, Sirui Zheng, Zhuoran Yang, Zhaoran Wang
Task Planning Environment Exploration Sparse Reward Sublinear Regret Online Reinforcement Learning Sample Efficient Deep RL Optimal Estimation Balancing Efficiency

May 16, 2023

A Deep RL Approach on Task Placement and Scaling of Edge Resources for Cellular Vehicle-to-Network Service Provisioning
Cyril Shih-Huan Hsu, Jorge Martín-Pérez, Danny De Vleeschauwer, Koteswararao Kondepu, Luca Valcarenghi, Xi Li, Chrysa Papagianni
Multiplicative Size Scaling New Resource Deep RL Global Placement

May 5, 2023

Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators
Alexander Herzog, Kanishka Rao, Karol Hausman, Yao Lu, Paul Wohlhart, Mengyuan Yan, Jessica Lin, Montserrat Gonzalez Arenas, Ted Xiao, Daniel Kappler, Daniel Ho, Jarek Rettinghouse, Yevgen Chebotar, Kuang-Huei Lee, Keerthana Gopalakrishnan, Ryan Julian, Adrian Li, Chuyuan Kelly Fu, Bob Wei, Sangeetha Ramesh, Khem Holden, Kim Kleiven, David Rendleman, Sean Kirmani, Jeff Bingham, Jon Weisz, Ying Xu, Wenlong Lu, Matthew Bennice, Cody Fong, David Do, Jessica Lam, Yunfei Bai, Benjie Holson, Michael Quinlan, Noah Brown, Mrinal Kalakrishnan, Julian Ibarz, Peter Pastor, Sergey Levine
Reinforcement Learning Deep Reinforcement Learning Large Scale Mobile Manipulator Deep RL Residential Building Manipulation Skill Efficient Waste

May 2, 2023

Unlocking the Power of Representations in Long-term Novelty-based Exploration
Alaa Saade, Steven Kapturowski, Daniele Calandriello, Charles Blundell, Pablo Sprechmann, Leopoldo Sarra, Oliver Groth, Michal Valko, Bilal Piot
Real Power Meaningful Representation Deep RL ATARI Game

April 26, 2023

Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning
Tuomas Haarnoja, Ben Moran, Guy Lever, Sandy H. Huang, Dhruva Tirumala, Jan Humplik, Markus Wulfmeier, Saran Tunyasuvunakool, Noah Y. Siegel, Roland Hafner, Michael Bloesch, Kristian Hartikainen, Arunkumar Byravan, Leonard Hasenclever, Yuval Tassa, Fereshteh Sadeghi, Nathan Batchelor, Federico Casarini, Stefano Saliceti, Charles Game, Neil Sreendra, Kushal Patel, Marlon Gwira, Andrea Huber, Nicole Hurley, Francesco Nori, Raia Hadsell, Nicolas Heess
Deep Reinforcement Learning Zero Shot Humanoid Robot Bipedal Robot Deep RL

April 20, 2023

Efficient Deep Reinforcement Learning Requires Regulating Overfitting
Qiyang Li, Aviral Kumar, Ilya Kostrikov, Sergey Levine
Deep Reinforcement Learning Model Overfitting Data Efficient Deep RL Sample Efficient Reinforcement Learning

March 6, 2023

Safe Reinforcement Learning via Probabilistic Logic Shields
Wen-Chi Yang, Giuseppe Marra, Gavin Rens, Luc De Raedt
Policy Gradient Safe Reinforcement Learning Deep RL Policy Gradient Algorithm Model Based Shielding Model Based Safe Reinforcement Learning

Deep RL

Papers

On Time-Indexing as Inductive Bias in Deep RL for Sequential Manipulation Tasks

Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines

Robust Network Slicing: Multi-Agent Policies, Adversarial Attacks, and Defensive Strategies

Towards model-free RL algorithms that scale well with unstructured data

Enhanced Low-Dimensional Sensing Mapless Navigation of Terrestrial Mobile Robots Using Double Deep Reinforcement Learning Techniques

Zero-Shot Transfer in Imitation Learning

Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games

Gray-box Adversarial Attack of Deep Reinforcement Learning-based Trading Agents

An AI Chatbot for Explaining Deep Reinforcement Learning Decisions of Service-oriented Systems

Learning Actions and Control of Focus of Attention with a Log-Polar-like Sensor

DoCRL: Double Critic Deep Reinforcement Learning for Mapless Navigation of a Hybrid Aerial Underwater Vehicle with Medium Transition

Resetting the Optimizer in Deep RL: An Empirical Study

AdaStop: adaptive statistical testing for sound comparisons of Deep RL agents

Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration

A Deep RL Approach on Task Placement and Scaling of Edge Resources for Cellular Vehicle-to-Network Service Provisioning

Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators

Unlocking the Power of Representations in Long-term Novelty-based Exploration

Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning

Efficient Deep Reinforcement Learning Requires Regulating Overfitting

Safe Reinforcement Learning via Probabilistic Logic Shields