Playing Games
 
Edit

Atari Games

277 papers with code • 64 benchmarks • 6 datasets

The Atari 2600 Games task (and dataset) involves training an agent to achieve high game scores.

( Image credit: Playing Atari with Deep Reinforcement Learning )

Libraries

Use these libraries to find Atari Games models and implementations
opendilab/DI-engine
12 papers
2,548
chainer/chainerrl
11 papers
1,154
NervanaSystems/coach
7 papers
2,309
chandar-lab/RLHive
7 papers
99
See all 24 libraries.

Datasets

Subtasks

Most implemented papers

Most implemented Social Latest No code

Soft Actor-Critic for Discrete Action Settings

p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch • • 16 Oct 2019

Soft Actor-Critic is a state-of-the-art reinforcement learning algorithm for continuous action settings that is not applicable to discrete action settings.

12
Paper
Code

ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning

mwydmuch/ViZDoom • • 6 May 2016

Here, we propose a novel test-bed platform for reinforcement learning research from raw visual information which employs the first-person perspective in a semi-realistic 3D world.

9
Paper
Code

Mastering Atari with Discrete World Models

danijar/dreamerv2 • • ICLR 2021

The world model uses discrete representations and is trained separately from the policy.

9
Paper
Code

Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

openai/baselines • • NeurIPS 2017

In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature.

8
Paper
Code

Accelerated Methods for Deep Reinforcement Learning

astooke/rlpyt • • 7 Mar 2018

Deep reinforcement learning (RL) has achieved many recent successes, yet experiment turn-around time remains a key bottleneck in research and in practice.

8
Paper
Code

Human level control through deep reinforcement learning

gordicaleksa/pytorch-learn-reinforcement-learning • • 25 Feb 2015

We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters.

7
Paper
Code

Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents

mgbellemare/Arcade-Learning-Environment • 18 Sep 2017

The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games.

7
Paper
Code

Fractal AI: A fragile theory of intelligence

FragileTheory/FractalAI • 13 Mar 2018

Fractal AI is a theory for general artificial intelligence.

7
Paper
Code

CURL: Contrastive Unsupervised Representations for Reinforcement Learning

MishaLaskin/curl • • 8 Apr 2020

On the DeepMind Control Suite, CURL is the first image-based algorithm to nearly match the sample-efficiency of methods that use state-based features.

7
Paper
Code

Deep Exploration via Bootstrapped DQN

tensorflow/models • • NeurIPS 2016

Efficient exploration in complex environments remains a major challenge for reinforcement learning.

6
Paper
Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy