Reinforcement Learning Environment

Reinforcement learning (RL) environments are simulated worlds designed to train RL agents, aiming to create realistic and challenging scenarios for efficient learning and robust policy development. Current research emphasizes improving data efficiency through techniques like curriculum learning and action masking, developing environments with complex, multi-objective structures (often incorporating safety mechanisms), and creating standardized, modular, and extensible frameworks for environment creation. These advancements are crucial for advancing RL research and enabling its application in diverse fields, from cybersecurity and robotics to supply chain optimization and design verification.

Papers

November 20, 2024

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
Davide Paglieri, Bartłomiej Cupiał, Samuel Coward, Ulyana Piterbarg, Maciej Wolczyk, Akbir Khan, Eduardo Pignatelli, Łukasz Kuciński, Lerrel Pinto, Rob Fergus, Jakob Nicolaus Foerster, Jack Parker-Holder, Tim Rocktäschel
Vision Language Model Video Game LLM Agent Spatial Reasoning Agent Capability Reinforcement Learning Environment

October 30, 2024

October 22, 2024

Benchmarking Smoothness and Reducing High-Frequency Oscillations in Continuous Control Policies
Guilherme Christmann, Ying-Sheng Luo, Hanjaya Mandala, Wei-Chao Chen
Reinforcement Learning Deep Reinforcement Learning Reinforcement Learning Environment Regularization Loss Non Converging Artificial Oscillation Continuous Control Policy

October 16, 2024

GAN Based Top-Down View Synthesis in Reinforcement Learning Environments
Usama Younus, Vinoj Jayasundara, Shivam Mishra, Suleyman Aslan
Novel View Synthesis Artificial Agent Reinforcement Learning Environment Reinforcement Learning Task

September 13, 2024

Applying Action Masking and Curriculum Learning Techniques to Improve Data Efficiency and Overall Performance in Operational Technology Cyber Security using Reinforcement Learning
Alec Wilson, William Holmes, Ryan Menzies, Kez Smithson Whitehead
Reinforcement Learning Reinforcement Learning Environment RL Agent Data Efficiency Action Masking

September 6, 2024

Stacked Universal Successor Feature Approximators for Safety in Reinforcement Learning
Ian Cannon, Washington Garcia, Thomas Gresavage, Joseph Saurine, Ian Leong, Jared Culbertson
Reinforcement Learning Human SAFETY Reinforcement Learning Agent Continuous Control Safety Critical Control Reinforcement Learning Environment Successor Representation

July 24, 2024

Gymnasium: A Standard Interface for Reinforcement Learning Environments
Mark Towers, Ariel Kwiatkowski, Jordan Terry, John U. Balis, Gianluca De Cola, Tristan Deleu, Manuel Goulão, Andreas Kallinteris, Markus Krimmel, Arjun KG, Rodrigo Perez-Vicente, Andrea Pierré, Sander Schulhoff, Jun Jet Tai, Hannah Tan, Omar G. Younis
Cognitive Abstraction Reinforcement Learning Environment Training Algorithm Standard Interface MR iNet Gym Benchmark Environment

July 4, 2024

Craftium: An Extensible Framework for Creating Reinforcement Learning Environments
Mikel Malagón, Josu Ceberio, Jose A. Lozano
Reinforcement Learning Reinforcement Learning Environment Extensible Framework Traditional CrAFT

June 18, 2024

Discovering Minimal Reinforcement Learning Environments
Jarek Liesen, Chris Lu, Andrei Lupu, Jakob N. Foerster, Henning Sprekeler, Robert T. Lange
Reinforcement Learning Markov Decision Process Contextual Bandit Reinforcement Learning Environment

May 30, 2024

Efficient Stimuli Generation using Reinforcement Learning in Design Verification
Deepak Narayan Gadde, Thomas Nalapat, Aman Kumar, Djones Lettnin, Wolfgang Kunz, Sebastian Simon
Reinforcement Learning Reinforcement Learning Environment System on Chip Stimulus Generation

January 17, 2024

DeLF: Designing Learning Environments with Foundation Models
Aida Afshar, Wenchao Li
Reinforcement Learning Foundation Model Action Space Sequential Decision Making Problem Reinforcement Learning Environment

December 4, 2023

Quality Diversity in the Amorphous Fortress (QD-AF): Evolving for Complexity in 0-Player Games
Sam Earle, M Charity, Dipika Rajesh, Mayu Wilson, Julian Togelius
Multi Agent Complexity Matter Quality Diversity Collective Behavior Reinforcement Learning Environment Two Player Competition Dynamic Amorphous Fortress

October 19, 2023

SDGym: Low-Code Reinforcement Learning Environments using System Dynamics Models
Emmanuel Klu, Sameer Sethi, DJ Passey, Donald Martin Jr
Reinforcement Learning Reinforcement Learning Environment System Dynamic Trained Policy

August 23, 2023

Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments
Maria Rigaki, Ondřej Lukáš, Carlos A. Catania, Sebastian Garcia
Multi Agent Scenario Reinforcement Learning Environment Security Game Net CAGE Cybersecurity Environment

August 7, 2023

AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning
Michaël Mathieu, Sherjil Ozair, Srivatsan Srinivasan, Caglar Gulcehre, Shangtong Zhang, Ray Jiang, Tom Le Paine, Richard Powell, Konrad Żołna, Julian Schrittwieser, David Choi, Petko Georgiev, Daniel Toyama, Aja Huang, Roman Ring, Igor Babuschkin, Timo Ewalds, Mahyar Bordbar, Sarah Henderson, Sergio Gómez Colmenarejo, Aäron van den Oord, Wojciech Marian Czarnecki, Nando de Freitas, Oriol Vinyals
Offline Reinforcement Learning Reinforcement Learning Environment StarCraft II Offline RL Algorithm Cloning Agent

June 24, 2023

Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks
Maxime Chevalier-Boisvert, Bolun Dai, Mark Towers, Rodrigo de Lazcano, Lucas Willems, Salem Lahlou, Suman Pal, Pablo Samuel Castro, Jordan Terry
2 Dimensional Modular System 3D Environment Reinforcement Learning Environment Goal Oriented Task MiniGrid Environment

June 14, 2023

OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments
Quentin Delfosse, Jannis Blüml, Bjarne Gregori, Sebastian Sztwiertnia, Kristian Kersting
Object Centric Representation Reinforcement Learning Environment Learning Environment State Object Composition

May 23, 2023

XRoute Environment: A Novel Reinforcement Learning Environment for Routing
Zhanwen Zhou, Hankz Hankui Zhuo, Xiaowu Zhang, Qiyuan Deng
Reinforcement Learning Routing Problem Reinforcement Learning Environment

May 3, 2023

Gym-preCICE: Reinforcement Learning Environments for Active Flow Control
Mosayeb Shams, Ahmed H. Elsheikh
Reinforcement Learning Reinforcement Learning Environment MR iNet Gym Active Flow Control Multi Physic Simulation

Reinforcement Learning Environment

Papers

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks

NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation

Benchmarking Smoothness and Reducing High-Frequency Oscillations in Continuous Control Policies

GAN Based Top-Down View Synthesis in Reinforcement Learning Environments

Applying Action Masking and Curriculum Learning Techniques to Improve Data Efficiency and Overall Performance in Operational Technology Cyber Security using Reinforcement Learning

Stacked Universal Successor Feature Approximators for Safety in Reinforcement Learning

Gymnasium: A Standard Interface for Reinforcement Learning Environments

Craftium: An Extensible Framework for Creating Reinforcement Learning Environments

Discovering Minimal Reinforcement Learning Environments

Efficient Stimuli Generation using Reinforcement Learning in Design Verification

DeLF: Designing Learning Environments with Foundation Models

Quality Diversity in the Amorphous Fortress (QD-AF): Evolving for Complexity in 0-Player Games

SDGym: Low-Code Reinforcement Learning Environments using System Dynamics Models

Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments

AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning

Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks

OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments

XRoute Environment: A Novel Reinforcement Learning Environment for Routing

Gym-preCICE: Reinforcement Learning Environments for Active Flow Control