Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
Datasets
State of the Art

Support

Contact
Pricing
Terms of Service
Privacy Policy
About

continuous-control-2

Car Racing

3260 papers • 126 benchmarks • 313 datasets

https://gym.openai.com/envs/CarRacing-v0/

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in continuous-control-2

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find continuous-control-2 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Simulated Car Racing Championship: Competition Software Manual

D. Loiacono, L. Cardamone, P. Lanzi•Thu Apr 04 2013

This manual describes the competition software for the Simulated Car Racing Championship and provides an overview of the architecture, the instructions to install the software and to run the simple drivers provided in the package.

110

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Car Racing | State-of-the-Art

Paper Graph

Deep neuroevolution of recurrent and discrete world models

S. Risi, Kenneth O. Stanley•Sat Apr 27 2019

This paper demonstrates the surprising finding that models with the same precise parts can be instead efficiently trained end-to-end through a genetic algorithm (GA), reaching a comparable performance to the original world model by solving a challenging car racing task.

56 0

Paper Graph

Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Function

Jun Zeng, Bike Zhang, K. Sreenath•Tue Jul 21 2020

This work presents a safety-critical model predictive control strategy utilizing discrete-time control barrier functions (CBFs), which guarantees system safety and accomplishes optimal performance via model predictivecontrol.

385 0

Paper Graph

Query-Efficient Imitation Learning for End-to-End Autonomous Driving

Kyunghyun Cho, Jiakai Zhang•Thu May 19 2016

An extension of the DAgger, called SafeDAgger, is proposed that is query-efficient and more suitable for end-to-end autonomous driving and observes a significant speed up in convergence, which is conjecture to be due to the effect of automated curriculum learning.

227 0

Paper Graph

Recurrent Environment Simulators

S. Chiappa, Daan Wierstra, S. Mohamed, S. Racanière•Thu Apr 06 2017

This work addresses the issue of computationally inefficiency with a model that does not need to generate a high-dimensional image at each time-step and can be used to improve exploration and is adaptable to many diverse environments.

219 0

Paper Graph

Deep Reinforcement Learning framework for Autonomous Driving

S. Yogamani, Ahmad El Sallab, Mohammed Abdou, E. Perot•Fri Apr 07 2017

The proposed framework for autonomous driving using deep reinforcement learning incorporates Recurrent Neural Networks for information integration, enabling the car to handle partially observable scenarios and integrates the recent work on attention models to focus on relevant information, thereby reducing the computational complexity for deployment on embedded hardware.

1017 0

Paper Graph

Interactive Learning with Corrective Feedback for Policies based on Deep Neural Networks

Rodrigo Pérez-Dattari, C. Celemin, Javier Ruiz-del-Solar, Jens Kober•Sat Sep 29 2018

This work approaches an alternative Interactive Machine Learning strategy for training DNN policies based on human corrective feedback, with a method called Deep COACH (D-COACH), which takes advantage of the knowledge and insights of human teachers as well as the power of DNNs, but also has no need of a reward function.

24 0

Paper Graph

Weight Agnostic Neural Networks

David R Ha, Adam Gaier•Mon Jun 10 2019

This work proposes a search method for neural network architectures that can already perform a task without any explicit weight training, and demonstrates that this method can find minimal neural network architecture that can perform several reinforcement learning tasks without weight training.

255 0

Paper Graph

Learning Human Objectives by Evaluating Hypothetical Behavior

S. Levine, Jan Leike, S. Legg, A. Dragan, S. Reddy•Wed Dec 04 2019

An algorithm that safely and interactively learns a model of the user's reward function and actively synthesizes hypothetical behaviors from scratch by maximizing tractable proxies for the value of information, without interacting with the environment.

79 0

Paper Graph

Adding a benchmark result helps the community track progress.