Playing Games
 
Edit

Atari Games

226 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
chainer/chainerrl
10 papers
1,058
NervanaSystems/coach
7 papers
2,159
chandar-lab/RLHive
7 papers
76
michaelnny/deep_rl_zoo
7 papers
12
See all 17 libraries.

Datasets

Subtasks

Most implemented papers

Most implemented Social Latest No code

Playing Atari with Deep Reinforcement Learning

ray-project/ray • 19 Dec 2013

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning.

96
Paper
Code

Deep Reinforcement Learning with Double Q-learning

labmlai/annotated_deep_learning_paper_implementations • • 22 Sep 2015

The popular Q-learning algorithm is known to overestimate action values under certain conditions.

88
Paper
Code

Prioritized Experience Replay

google/dopamine • • 18 Nov 2015

Experience replay lets online reinforcement learning agents remember and reuse experiences from the past.

70
Paper
Code

Dueling Network Architectures for Deep Reinforcement Learning

labmlai/annotated_deep_learning_paper_implementations • • 20 Nov 2015

In recent years there have been many successes of using deep representations in reinforcement learning.

68
Paper
Code

Asynchronous Methods for Deep Reinforcement Learning

ray-project/ray • 4 Feb 2016

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers.

67
Paper
Code

Rainbow: Combining Improvements in Deep Reinforcement Learning

thu-ml/tianshou • • 6 Oct 2017

The deep reinforcement learning community has made several independent improvements to the DQN algorithm.

29
Paper
Code

A Distributional Perspective on Reinforcement Learning

facebookresearch/Horizon • • ICML 2017

We obtain both state-of-the-art results and anecdotal evidence demonstrating the importance of the value distribution in approximate reinforcement learning.

21
Paper
Code

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

uber-research/coordconv • • NeurIPS 2018

In this paper we show a striking counterexample to this intuition via the seemingly trivial coordinate transform problem, which simply requires learning a mapping between coordinates in (x, y) Cartesian space and one-hot pixel space.

21
Paper
Code

Trust Region Policy Optimization

DLR-RM/stable-baselines3 • • 19 Feb 2015

We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement.

20
Paper
Code

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

deepmind/scalable_agent • • ICML 2018

In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters.

20
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