SOTAVerified

OpenAI Gym

An open-source toolkit from OpenAI that implements several Reinforcement Learning benchmarks including: classic control, Atari, Robotics and MuJoCo tasks.

(Description by Evolutionary learning of interpretable decision trees)

(Image Credit: OpenAI Gym)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–250 of 382 papers

TitleStatusHype
VisualEnv: visual Gym environments with Blender—0
DriverGym: Democratising Reinforcement Learning for Autonomous Driving—0
AWD3: Dynamic Reduction of the Estimation Bias—0
Proximal Policy Optimization with Continuous Bounded Action Space via the Beta Distribution—0
Machine Learning aided Crop Yield Optimization—0
DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention—0
REIN-2: Giving Birth to Prepared Reinforcement Learning Agents Using Reinforcement Learning Agents—0
Compositional Q-learning for electrolyte repletion with imbalanced patient sub-populations—0
Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks—0
Benchmarking Algorithms from Machine Learning for Low-Budget Black-Box Optimization—0
Hypothesis Driven Coordinate Ascent for Reinforcement Learning—0
Nested Policy Reinforcement Learning for Clinical Decision Support—0
Untangling Braids with Multi-agent Q-Learning—0
CrowdPlay: Crowdsourcing human demonstration data for offline learning in Atari games—0
Experience Replay More When It's a Key Transition in Deep Reinforcement Learning—0
Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic MethodsCode0
Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning—0
An Oracle and Observations for the OpenAI Gym / ALE Freeway Environment—0
Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge DistillationCode0
Photonic Quantum Policy Learning in OpenAI Gym—0
Influence-Based Reinforcement Learning for Intrinsically-Motivated Agents—0
An Independent Study of Reinforcement Learning and Autonomous Driving—0
An Analysis of Reinforcement Learning for Malaria Control—0
Constrained Policy Gradient Method for Safe and Fast Reinforcement Learning: a Neural Tangent Kernel Based ApproachCode0
Population-coding and Dynamic-neurons improved Spiking Actor Network for Reinforcement Learning—0
Offline Inverse Reinforcement Learning—0
Exploration and preference satisfaction trade-off in reward-free learning—0
AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning—0
Affine Transport for Sim-to-Real Domain Adaptation—0
A Generalised Inverse Reinforcement Learning Framework—0
Controlling an Inverted Pendulum with Policy Gradient Methods-A Tutorial—0
RAIL: A modular framework for Reinforcement-learning-based Adversarial Imitation Learning—0
Utilizing Skipped Frames in Action Repeats via Pseudo-Actions—0
Implementing Reinforcement Learning Algorithms in Retail Supply Chains with OpenAI Gym Toolkit—0
Reinforcement Learning using Guided Observability—0
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement LearningCode0
Optimism is All You Need: Model-Based Imitation Learning From Observation Alone—0
Foresee then Evaluate: Decomposing Value Estimation with Latent Future PredictionCode0
Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal LogicCode0
MobILE: Model-Based Imitation Learning From Observation AloneCode0
Sim-Env: Decoupling OpenAI Gym Environments from Simulation ModelsCode0
Transferring Domain Knowledge with an Adviser in Continuous Tasks—0
Learning from Demonstrations using Signal Temporal Logic—0
Neurogenetic Programming Framework for Explainable Reinforcement LearningCode0
Improving Reinforcement Learning with Human Assistance: An Argument for Human Subject Studies with HIPPO Gym—0
BF++: a language for general-purpose program synthesisCode0
Faults in Deep Reinforcement Learning Programs: A Taxonomy and A Detection ApproachCode0
Deep Q Learning from Dynamic Demonstration with Behavioral Cloning—0
Error Controlled Actor-Critic Method to Reinforcement Learning—0
Towards Understanding Asynchronous Advantage Actor-critic: Convergence and Linear Speedup—0
Show:102550
← PrevPage 5 of 8Next →
All datasetsAnt-v4HalfCheetah-v4Hopper-v4Humanoid-v4Walker2d-v4Ant-v2CartPole-v1HalfCheetah-v2Hopper-v2LunarLander-v2Mountain CarPendulum-v1

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MEowAverage Return6,586.33—Unverified
2TD3Average Return5,942.55—Unverified
3SACAverage Return5,208.09—Unverified
4DDPGAverage Return1,712.12—Unverified
5PPOAverage Return608.97—Unverified
#ModelMetricClaimedVerifiedStatus
1SACAverage Return15,836.04—Unverified
2DDPGAverage Return14,934.86—Unverified
3TD3Average Return12,026.73—Unverified
4MEowAverage Return10,981.47—Unverified
5PPOAverage Return6,006.11—Unverified
#ModelMetricClaimedVerifiedStatus
1MEowAverage Return3,332.99—Unverified
2TD3Average Return3,319.98—Unverified
3SACAverage Return2,882.56—Unverified
4DDPGAverage Return1,290.24—Unverified
5PPOAverage Return790.77—Unverified
#ModelMetricClaimedVerifiedStatus
1MEowAverage Return6,923.22—Unverified
2SACAverage Return6,211.5—Unverified
3PPOAverage Return925.89—Unverified
4TD3Average Return198.44—Unverified
5DDPGAverage Return139.14—Unverified
#ModelMetricClaimedVerifiedStatus
1SACAverage Return5,745.27—Unverified
2MEowAverage Return5,526.66—Unverified
3DDPGAverage Return2,994.54—Unverified
4PPOAverage Return2,739.81—Unverified
5TD3Average Return2,612.74—Unverified
#ModelMetricClaimedVerifiedStatus
1TLAMean Reward5,163.54—Unverified
2AWRMean Reward5,067—Unverified
#ModelMetricClaimedVerifiedStatus
1Orthogonal decision treeAverage Return500—Unverified
2Oblique decision treeAverage Return500—Unverified
#ModelMetricClaimedVerifiedStatus
1TLAMean Reward9,571.99—Unverified
2AWRMean Reward9,136—Unverified
#ModelMetricClaimedVerifiedStatus
1TLAMean Reward3,458.22—Unverified
2AWRMean Reward3,405—Unverified
#ModelMetricClaimedVerifiedStatus
1Oblique decision treeAverage Return272.14—Unverified
2AWRAverage Return229—Unverified
#ModelMetricClaimedVerifiedStatus
1Orthogonal decision treeAverage Return-101.72—Unverified
2Oblique decision treeAverage Return-106.02—Unverified
#ModelMetricClaimedVerifiedStatus
1TLA with Hierarchical Reward FunctionsMean Reward-125.02—Unverified
2TLAMean Reward-154.92—Unverified
#ModelMetricClaimedVerifiedStatus
1AWRMean Reward5,813—Unverified
2TLAMean Reward3,878.41—Unverified
#ModelMetricClaimedVerifiedStatus
1AWRAverage Return4,996—Unverified
#ModelMetricClaimedVerifiedStatus
1TLAMean Reward9,356.67—Unverified
#ModelMetricClaimedVerifiedStatus
1TLAMean Reward1,000—Unverified
#ModelMetricClaimedVerifiedStatus
1TLAMean Reward93.88—Unverified