Playing Atari with Deep Reinforcement Learning

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Atari Games	Atari 2600 Beam Rider	DQN Best	Score	5184	# 34
Atari Games	Atari 2600 Breakout	DQN Best	Score	225	# 36
Atari Games	Atari 2600 Enduro	DQN Best	Score	661	# 25
Atari Games	Atari 2600 Pong	DQN Best	Score	21	# 1
Atari Games	Atari 2600 Q*Bert	DQN Best	Score	4500	# 35
Atari Games	Atari 2600 Seaquest	DQN Best	Score	1740	# 33
Atari Games	Atari 2600 Space Invaders	DQN Best	Score	1075	# 36

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/playing-atari-with-deep-reinforcement/atari-games-on-atari-2600-pong)](https://paperswithcode.com/sota/atari-games-on-atari-2600-pong?p=playing-atari-with-deep-reinforcement)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/playing-atari-with-deep-reinforcement/atari-games-on-atari-2600-enduro)](https://paperswithcode.com/sota/atari-games-on-atari-2600-enduro?p=playing-atari-with-deep-reinforcement)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/playing-atari-with-deep-reinforcement/atari-games-on-atari-2600-seaquest)](https://paperswithcode.com/sota/atari-games-on-atari-2600-seaquest?p=playing-atari-with-deep-reinforcement)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/playing-atari-with-deep-reinforcement/atari-games-on-atari-2600-beam-rider)](https://paperswithcode.com/sota/atari-games-on-atari-2600-beam-rider?p=playing-atari-with-deep-reinforcement)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/playing-atari-with-deep-reinforcement/atari-games-on-atari-2600-qbert)](https://paperswithcode.com/sota/atari-games-on-atari-2600-qbert?p=playing-atari-with-deep-reinforcement)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/playing-atari-with-deep-reinforcement/atari-games-on-atari-2600-breakout)](https://paperswithcode.com/sota/atari-games-on-atari-2600-breakout?p=playing-atari-with-deep-reinforcement)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/playing-atari-with-deep-reinforcement/atari-games-on-atari-2600-space-invaders)](https://paperswithcode.com/sota/atari-games-on-atari-2600-space-invaders?p=playing-atari-with-deep-reinforcement)`

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards... (read more)

PDF Abstract

Code

Add Remove Mark official

tensorpack/tensorpack

5,933

hill-a/stable-baselines

↳ Quickstart in

Colab

2,925

lab-ml/nn

2,444

NervanaSystems/coach

1,924

DLR-RM/stable-baselines3

↳ Quickstart in

Colab

1,128

See all 80 implementations

Tasks

Add Remove

ATARI GAMES

Q-LEARNING

Datasets

Arcade Learning Environment

Results from the Paper

Edit

Ranked #1 on Atari Games on Atari 2600 Pong

Get a GitHub badge

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	BENCHMARK
Atari Games	Atari 2600 Beam Rider	DQN Best	Score	5184	# 34	Compare
Atari Games	Atari 2600 Breakout	DQN Best	Score	225	# 36	Compare
Atari Games	Atari 2600 Enduro	DQN Best	Score	661	# 25	Compare
Atari Games	Atari 2600 Pong	DQN Best	Score	21	# 1	Compare
Atari Games	Atari 2600 Q*Bert	DQN Best	Score	4500	# 35	Compare
Atari Games	Atari 2600 Seaquest	DQN Best	Score	1740	# 33	Compare
Atari Games	Atari 2600 Space Invaders	DQN Best	Score	1075	# 36	Compare

METHOD	TYPE
Epsilon Greedy Exploration	Behaviour Policies
Q-Learning	Off-Policy TD Control
Experience Replay	Replay Memory
Dense Connections	Feedforward Networks
Convolution	Convolutions
DQN	Q-Learning Networks

METHOD

TYPE

Epsilon Greedy Exploration