Atari Games

Edit

83 papers with code · Playing Games

Subtask of Video Games

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

State-of-the-art leaderboards

Add a result

Dataset	Best Method	Paper title	Compare
Atari 2600 Montezuma's Revenge	RND	Exploration by Random Network Distillation	See all
Atari 2600 Venture	RND	Exploration by Random Network Distillation	See all
Atari 2600 Freeway	TRPO-hash	#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning	See all
Atari 2600 Frostbite	Prior+Duel noop	Dueling Network Architectures for Deep Reinforcement Learning	See all
Atari 2600 Q*Bert	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Private Eye	C51 noop	A Distributional Perspective on Reinforcement Learning	See all
Atari 2600 Gravitar	RND	Exploration by Random Network Distillation	See all
Atari 2600 Seaquest	C51 noop	A Distributional Perspective on Reinforcement Learning	See all
Atari 2600 Space Invaders	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Enduro	C51 noop	A Distributional Perspective on Reinforcement Learning	See all
Atari 2600 Pong	DQN best	Playing Atari with Deep Reinforcement Learning	See all
Atari 2600 Amidar	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Asterix	C51 noop	A Distributional Perspective on Reinforcement Learning	See all
Atari 2600 Breakout	Bootstrapped DQN	Deep Exploration via Bootstrapped DQN	See all
Atari 2600 Alien	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Assault	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Beam Rider	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Kangaroo	Prior noop	Prioritized Experience Replay	See all
Atari 2600 Gopher	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Robotank	Bootstrapped DQN	Deep Exploration via Bootstrapped DQN	See all
Atari 2600 Bowling	DDQN+Pop-Art noop	Learning values across many orders of magnitude	See all
Atari 2600 Up and Down	A3C LSTM hs	Asynchronous Methods for Deep Reinforcement Learning	See all
Atari 2600 Tutankham	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Time Pilot	A3C LSTM hs	Asynchronous Methods for Deep Reinforcement Learning	See all
Atari 2600 Name This Game	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Boxing	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Asteroids	A3C LSTM hs	Asynchronous Methods for Deep Reinforcement Learning	See all
Atari 2600 Zaxxon	A3C FF hs	Asynchronous Methods for Deep Reinforcement Learning	See all
Atari 2600 Ice Hockey	Prior noop	Prioritized Experience Replay	See all
Atari 2600 Tennis	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Road Runner	A3C LSTM hs	Asynchronous Methods for Deep Reinforcement Learning	See all
Atari 2600 Krull	Duel noop	Dueling Network Architectures for Deep Reinforcement Learning	See all
Atari 2600 Demon Attack	C51 noop	A Distributional Perspective on Reinforcement Learning	See all
Atari 2600 Crazy Climber	C51 noop	A Distributional Perspective on Reinforcement Learning	See all
Atari 2600 Centipede	DDQN+Pop-Art noop	Learning values across many orders of magnitude	See all
Atari 2600 River Raid	Duel noop	Dueling Network Architectures for Deep Reinforcement Learning	See all
Atari 2600 Wizard of Wor	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Double Dunk	Prior noop	Prioritized Experience Replay	See all
Atari 2600 Battle Zone	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Video Pinball	C51 noop	A Distributional Perspective on Reinforcement Learning	See all
Atari 2600 Bank Heist	Duel noop	Dueling Network Architectures for Deep Reinforcement Learning	See all
Atari 2600 Atlantis	ES FF (1 hour) noop	Evolution Strategies as a Scalable Alternative to Reinforcement Learning	See all
Atari 2600 Star Gunner	A3C LSTM hs	Asynchronous Methods for Deep Reinforcement Learning	See all
Atari 2600 Fishing Derby	Duel noop	Dueling Network Architectures for Deep Reinforcement Learning	See all
Atari 2600 Chopper Command	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Kung-Fu Master	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 HERO	C51 noop	A Distributional Perspective on Reinforcement Learning	See all
Atari 2600 Ms. Pacman	Prior noop	Prioritized Experience Replay	See all
Atari 2600 James Bond	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Berzerk	Prior+Duel noop	Dueling Network Architectures for Deep Reinforcement Learning	See all
Atari 2600 Defender	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari-57	Ape-X	Distributed Prioritized Experience Replay	See all
Atari 2600 Solaris	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Phoenix	Prior+Duel hs	Dueling Network Architectures for Deep Reinforcement Learning	See all
Atari 2600 Pitfall!	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Skiing	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Yars Revenge	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all
Atari 2600 Surround	IQN	Implicit Quantile Networks for Distributional Reinforcement Learning	See all

Subtasks

Montezuma's Revenge

8 papers with code

Latest papers with code

Reusing Convolutional Activations from Frame to Frame to Speed up Training and Inference

2 Sep 2019 • arnokha/reusing_convolutions •

When processing similar frames in succession, we can take advantage of the locality of the convolution operation to reevaluate only portions of the image that changed from the previous frame.

ATARI GAMES TIME SERIES

02 Sep 2019

Paper
Code

GPU-Accelerated Atari Emulation for Reinforcement Learning

19 Jul 2019 • NVLABs/cule •

We designed and implemented a CUDA port of the Atari Learning Environment (ALE), a system for developing and evaluating deep reinforcement algorithms using Atari games.

ATARI GAMES

19 Jul 2019

Paper
Code

Striving for Simplicity in Off-policy Deep Reinforcement Learning

10 Jul 2019 • google-research/batch_rl •

Second, how much of the benefits of recent distributional RL algorithms is attributed to improvements in exploration versus exploitation behavior?

ATARI GAMES Q-LEARNING

10 Jul 2019

Paper
Code

Unsupervised State Representation Learning in Atari

19 Jun 2019 • ankeshanand/atari-representation-learning •

State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks.

ATARI GAMES REPRESENTATION LEARNING

19 Jun 2019

Paper
Code

Exploration via Flow-Based Intrinsic Rewards

24 May 2019 • hellochick/MarioO_O-flow-curioisty •

Exploration bonuses derived from the novelty of observations in an environment have become a popular approach to motivate exploration for reinforcement learning (RL) agents in the past few years.

ATARI GAMES OPTICAL FLOW ESTIMATION

24 May 2019

Paper
Code

Combining Experience Replay with Exploration by Random Network Distillation

18 May 2019 • Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation- •

Our work is a simple extension of the paper "Exploration by Random Network Distillation".

MONTEZUMA'S REVENGE

18 May 2019

Paper
Code

Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments

12 Apr 2019 • kclary/variability-RL

Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itself have led researchers to report the performance of learned agents using aggregate metrics of performance over multiple random seeds for a single environment.

ATARI GAMES

12 Apr 2019

Paper
Code

Deep Policies for Width-Based Planning in Pixel Domains

12 Apr 2019 • aig-upf/pi-IW •

Surprisingly, we observe that the representation learned by the neural network can be used as a feature space for the width-based planner without degrading its performance, thus removing the requirement of pre-defined features for the planner.

ATARI GAMES

12 Apr 2019

Paper
Code

MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments

7 Mar 2019 • kenjyoung/MinAtar •

With the representation learning problem simplified, we can perform experiments with significantly less computational expense.

ATARI GAMES REPRESENTATION LEARNING

07 Mar 2019

Paper
Code

Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning

4 Feb 2019 • dazcona/obstacletower

Unlike other benchmarks such as the Arcade Learning Environment, evaluation of agent performance in Obstacle Tower is based on an agent's ability to perform well on unseen instances of the environment.

ATARI GAMES BOARD GAMES

04 Feb 2019

Paper
Code

Atari Games Edit

State-of-the-art leaderboards Add a result

Subtasks

Montezuma's Revenge

Latest papers with code

Atari Games

Edit

State-of-the-art leaderboards

Add a result