Continuous Control

Edit

208 papers with code • 73 benchmarks • 7 datasets

This task has no description! Would you like to contribute one?

Benchmarks

Add a Result

Dataset	Best Model	Paper Title	Compare
PyBullet HalfCheetah	SAC	Smooth Exploration for Robotic Reinforcement Learning	See all
PyBullet Walker2D	SAC gSDE	Smooth Exploration for Robotic Reinforcement Learning	See all
PyBullet Ant	SAC gSDE	Smooth Exploration for Robotic Reinforcement Learning	See all
PyBullet Hopper	SAC gSDE	Smooth Exploration for Robotic Reinforcement Learning	See all
DeepMind Cheetah Run (Images)	DrQ	Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels	See all
DeepMind Cup Catch (Images)	DrQ	Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels	See all
DeepMind Walker Walk (Images)	DrQ	Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels	See all
cartpole.swingup	SMuZero	Learning and Planning in Complex Action Spaces	See all
cheetah.run	SMuZero	Learning and Planning in Complex Action Spaces	See all
finger.turn_hard	SMuZero	Learning and Planning in Complex Action Spaces	See all
walker.stand	SMuZero	Learning and Planning in Complex Action Spaces	See all
walker.walk	SMuZero	Learning and Planning in Complex Action Spaces	See all
Cart-Pole Balancing	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Inverted Pendulum	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Mountain Car	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Acrobot	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Double Inverted Pendulum	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Swimmer	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Hopper	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
2D Walker	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Half-Cheetah	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Ant	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Simple Humanoid	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Full Humanoid	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Cart-Pole Balancing (limited sensors)	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Inverted Pendulum (limited sensors)	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Mountain Car (limited sensors)	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Acrobot (limited sensors)	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Cart-Pole Balancing (noisy observations)	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Inverted Pendulum (noisy observations)	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Mountain Car (noisy observations)	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Acrobot (noisy observations)	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Cart-Pole Balancing (system identifications)	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Inverted Pendulum (system identifications)	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Mountain Car (system identifications)	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Acrobot (system identifications)	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Swimmer + Gathering	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Ant + Gathering	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Swimmer + Maze	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Ant + Maze	TRPO	Benchmarking Deep Reinforcement Learning for Continuous Control	See all
Cart Pole (OpenAI Gym)	MAC	Mean Actor Critic	See all
Lunar Lander (OpenAI Gym)	MAC	Mean Actor Critic	See all
Finger, spin (DMControl500k)	CURL	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	See all
Cartpole, swingup (DMControl500k)	CURL	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	See all
Reacher, easy (DMControl500k)	CURL	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	See all
Cheetah, run (DMControl500k)	CURL	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	See all
Walker, walk (DMControl500k)	CURL	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	See all
Ball in cup, catch (DMControl500k)	CURL	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	See all
Finger, spin (DMControl100k)	CURL	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	See all
Cartpole, swingup (DMControl100k)	CURL	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	See all
Reacher, easy (DMControl100k)	CURL	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	See all
Cheetah, run (DMControl100k)	CURL	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	See all
Walker, walk (DMControl100k)	CURL	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	See all
Ball in cup, catch (DMControl100k)	CURL	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	See all
acrobot.swingup	SMuZero	Learning and Planning in Complex Action Spaces	See all
cartpole.balance	SMuZero	Learning and Planning in Complex Action Spaces	See all
cartpole.balance_sparse	SMuZero	Learning and Planning in Complex Action Spaces	See all
cartpole.swingup_sparse	SMuZero	Learning and Planning in Complex Action Spaces	See all
ball_in_cup.catch	SMuZero	Learning and Planning in Complex Action Spaces	See all
finger.spin	SMuZero	Learning and Planning in Complex Action Spaces	See all
finger.turn_easy	SMuZero	Learning and Planning in Complex Action Spaces	See all
hopper.hop	SMuZero	Learning and Planning in Complex Action Spaces	See all
hopper.stand	SMuZero	Learning and Planning in Complex Action Spaces	See all
pendulum.swingup	SMuZero	Learning and Planning in Complex Action Spaces	See all
quadruped.run	SMuZero	Learning and Planning in Complex Action Spaces	See all
quadruped.walk	SMuZero	Learning and Planning in Complex Action Spaces	See all
reacher.easy	SMuZero	Learning and Planning in Complex Action Spaces	See all
reacher.hard	SMuZero	Learning and Planning in Complex Action Spaces	See all
walker.run	SMuZero	Learning and Planning in Complex Action Spaces	See all
fish.swim	MuZero Unplugged	Online and Offline Reinforcement Learning by Planning with a Learned Model	See all
manipulator.insert_ball	MuZero Unplugged	Online and Offline Reinforcement Learning by Planning with a Learned Model	See all
manipulator.insert_peg	MuZero Unplugged	Online and Offline Reinforcement Learning by Planning with a Learned Model	See all
humanoid.run	MuZero Unplugged	Online and Offline Reinforcement Learning by Planning with a Learned Model	See all

Show all 73 benchmarks

Collapse benchmarks

Datasets

Subtasks

Greatest papers with code

Near-Optimal Representation Learning for Hierarchical Reinforcement Learning

tensorflow/models • • ICLR 2019

We study the problem of representation learning in goal-conditioned hierarchical reinforcement learning.

Continuous Control Hierarchical Reinforcement Learning +1

70,753

Paper
Code

Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion

tensorflow/models • • NeurIPS 2018

Integrating model-free and model-based approaches in reinforcement learning has the potential to achieve the high performance of model-free algorithms with low sample complexity.

Continuous Control

70,751

Paper
Code

Trust-PCL: An Off-Policy Trust Region Method for Continuous Control

tensorflow/models • • ICLR 2018

When evaluated on a number of continuous control tasks, Trust-PCL improves the solution quality and sample efficiency of TRPO.

Continuous Control

70,751

Paper
Code

Parameter Space Noise for Exploration

tensorflow/models • • ICLR 2018

Combining parameter noise with traditional RL methods allows to combine the best of both worlds.

Continuous Control

70,751

Paper
Code

Primal Wasserstein Imitation Learning

google-research/google-research • • ICLR 2021

Imitation Learning (IL) methods seek to match the behavior of an agent with that of an expert.

Continuous Control Imitation Learning

18,571

Paper
Code

Behavior Regularized Offline Reinforcement Learning

google-research/google-research • • 26 Nov 2019

In reinforcement learning (RL) research, it is common to assume access to direct online interactions with the environment.

Continuous Control Offline RL

18,571

Paper
Code

Unsupervised Learning of Object Structure and Dynamics from Videos

google-research/google-research • • NeurIPS 2019

Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning.

Action Recognition Continuous Control +2

18,571

Paper
Code

Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

google/trax • • 1 Oct 2019

In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines.

Ranked #1 on OpenAI Gym on HalfCheetah-v2

Continuous Control OpenAI Gym

6,339

Paper
Code

High-Dimensional Continuous Control Using Generalized Advantage Estimation

lab-ml/nn • • 8 Jun 2015

Policy gradient methods are an appealing approach in reinforcement learning because they directly optimize the cumulative reward and can straightforwardly be used with nonlinear function approximators such as neural networks.

Continuous Control Policy Gradient Methods

3,304

Paper
Code

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

hill-a/stable-baselines • • ICML 2018

A platform for Applied Reinforcement Learning (Applied RL)

Continuous Control Decision Making +2

3,226

Paper
Code

Continuous Control Edit

Benchmarks Add a Result

Datasets

Subtasks

Greatest papers with code

Continuous Control

Edit

Benchmarks

Add a Result