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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 326–350 of 382 papers

Title	Date	Tasks	Status
Towards Characterizing Divergence in Deep Q-Learning	Mar 21, 2019	continuous-controlContinuous Control	—Unverified
Deep Reinforcement Learning with Feedback-based Exploration	Mar 14, 2019	continuous-controlContinuous Control	CodeCode Available
gym-gazebo2, a toolkit for reinforcement learning using ROS 2 and Gazebo	Mar 14, 2019	BenchmarkingOpenAI Gym	CodeCode Available
Learning Gaussian Policies from Corrective Human Feedback	Mar 12, 2019	continuous-controlContinuous Control	—Unverified
Deep Active Localization	Mar 5, 2019	OpenAI GymReinforcement Learning	CodeCode Available
Flappy Hummingbird: An Open Source Dynamic Simulation of Flapping Wing Robots and Animals	Feb 25, 2019	Deep Reinforcement LearningOpenAI Gym	CodeCode Available
Curiosity-Driven Experience Prioritization via Density Estimation	Feb 20, 2019	Density EstimationOpenAI Gym	—Unverified
Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement Learning	Feb 15, 2019	Deep Reinforcement LearningImitation Learning	CodeCode Available
Learn a Prior for RHEA for Better Online Planning	Feb 14, 2019	Evolutionary AlgorithmsMuJoCo	—Unverified
Towards Physically Safe Reinforcement Learning under Supervision	Jan 19, 2019	OpenAI Gymreinforcement-learning	—Unverified
Deconfounding Reinforcement Learning in Observational Settings	Dec 26, 2018	OpenAI Gymreinforcement-learning	CodeCode Available
Iroko: A Framework to Prototype Reinforcement Learning for Data Center Traffic Control	Dec 24, 2018	Deep Reinforcement LearningOpenAI Gym	CodeCode Available
Relative Entropy Regularized Policy Iteration	Dec 5, 2018	continuous-controlContinuous Control	CodeCode Available
BlockPuzzle - A Challenge in Physical Reasoning and Generalization for Robot Learning	Nov 30, 2018	Imitation LearningMuJoCo	—Unverified
Relative Importance Sampling for off-Policy Actor-Critic in Deep Reinforcement Learning	Oct 30, 2018	Deep Reinforcement LearningOpenAI Gym	—Unverified
Sequential Learning of Movement Prediction in Dynamic Environments using LSTM Autoencoder	Oct 12, 2018	DecoderNavigate	—Unverified
Reinforcement Learning for Improving Agent Design	Oct 9, 2018	OpenAI Gymreinforcement-learning	CodeCode Available
Hybrid Policies Using Inverse Rewards for Reinforcement Learning	Sep 27, 2018	OpenAI GymQ-Learning	—Unverified
Switching Isotropic and Directional Exploration with Parameter Space Noise in Deep Reinforcement Learning	Sep 18, 2018	Deep Reinforcement LearningOpenAI Gym	—Unverified
Visual Transfer between Atari Games using Competitive Reinforcement Learning	Sep 2, 2018	Atari GamesDeep Reinforcement Learning	CodeCode Available
GeneSys: Enabling Continuous Learning through Neural Network Evolution in Hardware	Aug 3, 2018	CPUGPU	—Unverified
FuzzerGym: A Competitive Framework for Fuzzing and Learning	Jul 19, 2018	Deep Reinforcement LearningFault Detection	—Unverified
Online Robust Policy Learning in the Presence of Unknown Adversaries	Jul 16, 2018	Deep Reinforcement LearningOpenAI Gym	—Unverified
Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Network	Jun 14, 2018	OpenAI Gymreinforcement-learning	—Unverified
Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces	Jun 8, 2018	Atari GamesGaussian Processes	—Unverified

Show:10 25 50

← PrevPage 14 of 16Next →

All datasets Ant-v4 HalfCheetah-v4 Hopper-v4 Humanoid-v4 Walker2d-v4 Ant-v2 CartPole-v1 HalfCheetah-v2 Hopper-v2 LunarLander-v2 Mountain Car Pendulum-v1

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	MEow	Average Return	6,586.33	—	Unverified
2	TD3	Average Return	5,942.55	—	Unverified
3	SAC	Average Return	5,208.09	—	Unverified
4	DDPG	Average Return	1,712.12	—	Unverified
5	PPO	Average Return	608.97	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SAC	Average Return	15,836.04	—	Unverified
2	DDPG	Average Return	14,934.86	—	Unverified
3	TD3	Average Return	12,026.73	—	Unverified
4	MEow	Average Return	10,981.47	—	Unverified
5	PPO	Average Return	6,006.11	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MEow	Average Return	3,332.99	—	Unverified
2	TD3	Average Return	3,319.98	—	Unverified
3	SAC	Average Return	2,882.56	—	Unverified
4	DDPG	Average Return	1,290.24	—	Unverified
5	PPO	Average Return	790.77	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MEow	Average Return	6,923.22	—	Unverified
2	SAC	Average Return	6,211.5	—	Unverified
3	PPO	Average Return	925.89	—	Unverified
4	TD3	Average Return	198.44	—	Unverified
5	DDPG	Average Return	139.14	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SAC	Average Return	5,745.27	—	Unverified
2	MEow	Average Return	5,526.66	—	Unverified
3	DDPG	Average Return	2,994.54	—	Unverified
4	PPO	Average Return	2,739.81	—	Unverified
5	TD3	Average Return	2,612.74	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TLA	Mean Reward	5,163.54	—	Unverified
2	AWR	Mean Reward	5,067	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Orthogonal decision tree	Average Return	500	—	Unverified
2	Oblique decision tree	Average Return	500	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TLA	Mean Reward	9,571.99	—	Unverified
2	AWR	Mean Reward	9,136	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TLA	Mean Reward	3,458.22	—	Unverified
2	AWR	Mean Reward	3,405	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Oblique decision tree	Average Return	272.14	—	Unverified
2	AWR	Average Return	229	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Orthogonal decision tree	Average Return	-101.72	—	Unverified
2	Oblique decision tree	Average Return	-106.02	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TLA with Hierarchical Reward Functions	Mean Reward	-125.02	—	Unverified
2	TLA	Mean Reward	-154.92	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	AWR	Mean Reward	5,813	—	Unverified
2	TLA	Mean Reward	3,878.41	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	AWR	Average Return	4,996	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TLA	Mean Reward	9,356.67	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TLA	Mean Reward	1,000	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TLA	Mean Reward	93.88	—	Unverified