OpenAI Gym

Abstract

OpenAI Gym is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can share their results and compare the performance of algorithms. This whitepaper discusses the components of OpenAI Gym and the design decisions that went into the software.

Cited by in corpus (120)

• A Brief Survey of Deep Reinforcement Learning
• AutoML: A Survey of the State-of-the-Art
• ChatGPT and a New Academic Reality: Artificial Intelligence-Written Research Papers and the Ethics of the Large Language Models in Scholarly Publishing
• A Survey and Critique of Multiagent Deep Reinforcement Learning
• How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned
• Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges
• A Closer Look at Invalid Action Masking in Policy Gradient Algorithms
• Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors
• Character Controllers Using Motion VAEs
• Deep Reinforcement Learning Attitude Control of Fixed-Wing UAVs Using Proximal Policy Optimization
• Quantum agents in the Gym: a variational quantum algorithm for deep Q-learning
• Flow: A Modular Learning Framework for Mixed Autonomy Traffic
• A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
• Large-Scale Traffic Signal Control Using a Novel Multi-Agent Reinforcement Learning
• Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning
• Optimal control towards sustainable wastewater treatment plants based on multi-agent reinforcement learning
• A Survey of Algorithms for Black-Box Safety Validation of Cyber-Physical Systems
• Building HVAC Scheduling Using Reinforcement Learning via Neural Network Based Model Approximation
• Variational Quantum Reinforcement Learning via Evolutionary Optimization
• Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning
• Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation
• Measurement Based Feedback Quantum Control With Deep Reinforcement Learning for Double-well Non-linear Potential
• Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning
• Deep Reinforcement Learning Control of Quantum Cartpoles
• Single-step deep reinforcement learning for open-loop control of laminar and turbulent flows
• CityLearn v2: Energy-flexible, resilient, occupant-centric, and carbon-aware management of grid-interactive communities
• Neurosymbolic Reinforcement Learning and Planning: A Survey
• Accelerating Reinforcement Learning for Reaching using Continuous Curriculum Learning
• Longitudinal Dynamic versus Kinematic Models for Car-Following Control Using Deep Reinforcement Learning
• Gym-ANM: Reinforcement Learning Environments for Active Network Management Tasks in Electricity Distribution Systems
• Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning
• Towards a Common Implementation of Reinforcement Learning for Multiple Robotic Tasks
• Inclined Quadrotor Landing using Deep Reinforcement Learning
• Creating Valid Adversarial Examples of Malware
• Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks
• Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution
• Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Network
• Gym-Ignition: Reproducible Robotic Simulations for Reinforcement Learning
• Revisiting State Augmentation methods for Reinforcement Learning with Stochastic Delays
• Benchmarking projective simulation in navigation problems
• Evolutionary reinforcement learning of dynamical large deviations
• Reinforcement Learning-based Placement of Charging Stations in Urban Road Networks
• Exploration of Artificial Intelligence-oriented Power System Dynamic Simulators
• ABIDES-Gym: Gym Environments for Multi-Agent Discrete Event Simulation and Application to Financial Markets
• Auxiliary-task Based Deep Reinforcement Learning for Participant Selection Problem in Mobile Crowdsourcing
• Evolutionary Quantum Architecture Search for Parametrized Quantum Circuits
• Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization
• A Centralised Soft Actor Critic Deep Reinforcement Learning Approach to District Demand Side Management through CityLearn
• Illustrated tutorial on global optimization in nanophotonics
• Generalization in Transfer Learning
• Jet grooming through reinforcement learning
• Optimizing Throughput Performance in Distributed MIMO Wi-Fi Networks using Deep Reinforcement Learning
• EvoJAX: Hardware-Accelerated Neuroevolution
• Motion Planning by Reinforcement Learning for an Unmanned Aerial Vehicle in Virtual Open Space with Static Obstacles
• Robotic Table Tennis: A Case Study into a High Speed Learning System
• Structure in Deep Reinforcement Learning: A Survey and Open Problems
• Quantum reinforcement learning in continuous action space
• Energy-Aware Adaptive Sampling for Self-Sustainability in Resource-Constrained IoT Devices
• Generation of ice states through deep reinforcement learning
• Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments
• Evaluating Deception and Moving Target Defense with Network Attack Simulation
• Revisiting Maximum Entropy Inverse Reinforcement Learning: New Perspectives and Algorithms
• Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods
• Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions
• TC-Driver: Trajectory Conditioned Driving for Robust Autonomous Racing -- A Reinforcement Learning Approach
• CoRe Optimizer: An All-in-One Solution for Machine Learning
• AutoDOViz: Human-Centered Automation for Decision Optimization
• Skip Training for Multi-Agent Reinforcement Learning Controller for Industrial Wave Energy Converters
• Optimizing with Low Budgets: a Comparison on the Black-box Optimization Benchmarking Suite and OpenAI Gym
• ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning
• SOCKS: A Stochastic Optimal Control and Reachability Toolbox Using Kernel Methods
• Variational Quantum Circuit Design for Quantum Reinforcement Learning on Continuous Environments
• The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning
• Design Space Exploration of Approximate Computing Techniques with a Reinforcement Learning Approach
• Investigation of reinforcement learning for shape optimization of profile extrusion dies
• An Embedded Feature Selection Framework for Control
• HyperNCA: Growing Developmental Networks with Neural Cellular Automata
• Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning
• Error-based or target-based? A unifying framework for learning in recurrent spiking networks
• Adaptive Road Configurations for Improved Autonomous Vehicle-Pedestrian Interactions using Reinforcement Learning
• Deep Reinforcement Learning with Feedback-based Exploration
• Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL
• Offline Reinforcement Learning with Pseudometric Learning
• CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing
• Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures
• Gym-saturation: an OpenAI Gym environment for saturation provers
• Learning to Deceive in Multi-Agent Hidden Role Games
• Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning
• Deep Inductive Logic Programming meets Reinforcement Learning
• A NEAT Quantum Error Decoder
• Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers
• Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning
• Online Baum-Welch algorithm for Hierarchical Imitation Learning
• Reinforcement Learning reveals fundamental limits on the mixing of active particles
• A Machine with Short-Term, Episodic, and Semantic Memory Systems
• PAC-Bayesian Soft Actor-Critic Learning
• Learning to Act through Evolution of Neural Diversity in Random Neural Networks
• Peer Learning: Learning Complex Policies in Groups from Scratch via Action Recommendations
• Expert-Guided Symmetry Detection in Markov Decision Processes
• Smooth Imitation Learning via Smooth Costs and Smooth Policies
• Learning cooperative behaviours in adversarial multi-agent systems
• Criticality as It Could Be: organizational invariance as self-organized criticality in embodied agents
• Data Augmentation through Expert-guided Symmetry Detection to Improve Performance in Offline Reinforcement Learning
• Path Following and Stabilisation of a Bicycle Model using a Reinforcement Learning Approach
• Autonomous Learning of Features for Control: Experiments with Embodied and Situated Agents
• Self-building Neural Networks
• Energy-Efficient Parking Analytics System using Deep Reinforcement Learning
• An Active Learning Framework for Efficient Robust Policy Search
• The Temporal Singularity: time-accelerated simulated civilizations and their implications
• Minimal Neural Network Models for Permutation Invariant Agents
• Reversible and irreversible bracket-based dynamics for deep graph neural networks
• Emergent Behaviors in Multi-Agent Target Acquisition
• A Theory of Non-Acyclic Generative Flow Networks
• Optimal operation of cryogenic calorimeters through deep reinforcement learning
• Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration
• The Quantum Cartpole: A benchmark environment for non-linear reinforcement learning
• Learning in Sparse Rewards settings through Quality-Diversity algorithms
• Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders
• gym-saturation: Gymnasium environments for saturation provers (System description)
• Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models