Atari Games

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

( Image credit: Playing Atari with Deep Reinforcement Learning )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 401–425 of 625 papers

Title	Date	Tasks	Status
Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policy	Nov 10, 2019	Adversarial AttackAtari Games	—Unverified
Fully Parameterized Quantile Function for Distributional Reinforcement Learning	Nov 5, 2019	Atari GamesDistributional Reinforcement Learning	CodeCode Available
ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations	Oct 26, 2019	Atari GamesDeep Reinforcement Learning	CodeCode Available
Momentum-based Accelerated Q-learning	Oct 23, 2019	Atari GamesQ-Learning	CodeCode Available
Momentum in Reinforcement Learning	Oct 21, 2019	Atari Gamesreinforcement-learning	—Unverified
Soft Actor-Critic for Discrete Action Settings	Oct 16, 2019	Atari Gamesreinforcement-learning	CodeCode Available
Parallel Exploration via Negatively Correlated Search	Oct 16, 2019	Atari GamesDiversity	—Unverified
Reinforcement Learning with Structured Hierarchical Grammar Representations of Actions	Oct 7, 2019	Atari GamesQ-Learning	—Unverified
Formal Language Constraints for Markov Decision Processes	Oct 2, 2019	Atari GamesMuJoCo	CodeCode Available
Playing Atari Ball Games with Hierarchical Reinforcement Learning	Sep 27, 2019	Atari GamesHierarchical Reinforcement Learning	—Unverified
Harnessing Structures for Value-Based Planning and Reinforcement Learning	Sep 26, 2019	Atari GamesDeep Reinforcement Learning	CodeCode Available
Striving for Simplicity in Off-Policy Deep Reinforcement Learning	Sep 25, 2019	Atari GamesDeep Reinforcement Learning	—Unverified
CAN ALTQ LEARN FASTER: EXPERIMENTS AND THEORY	Sep 25, 2019	Atari GamesQ-Learning	—Unverified
Off-Policy Actor-Critic with Shared Experience Replay	Sep 25, 2019	Atari GamesReinforcement Learning	—Unverified
Regulatory Focus: Promotion and Prevention Inclinations in Policy Search	Sep 25, 2019	Atari Gamescontinuous-control	—Unverified
Learning Key Steps to Attack Deep Reinforcement Learning Agents	Sep 25, 2019	Adversarial AttackAtari Games	—Unverified
Recurrent Independent Mechanisms	Sep 24, 2019	Atari Games	CodeCode Available
Active inference: demystified and compared	Sep 24, 2019	Atari GamesOpenAI Gym	CodeCode Available
Biased Estimates of Advantages over Path Ensembles	Sep 15, 2019	Atari Gamescontinuous-control	—Unverified
Reinforcement Learning and Video Games	Sep 10, 2019	Atari GamesDeep Learning	—Unverified
LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Games	Sep 4, 2019	Atari GamesDeep Reinforcement Learning	—Unverified
Reusing Convolutional Activations from Frame to Frame to Speed up Training and Inference	Sep 2, 2019	Atari GamesTime Series	CodeCode Available
Performing Deep Recurrent Double Q-Learning for Atari Games	Aug 16, 2019	Atari GamesDeep Reinforcement Learning	CodeCode Available
Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing field	Aug 13, 2019	Atari GamesDeep Reinforcement Learning	CodeCode Available
Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment	Aug 6, 2019	Atari GamesBenchmarking	—Unverified

Show:10 25 50

← PrevPage 17 of 25Next →

All datasets Atari 2600 Breakout Atari 2600 Freeway Atari 2600 Q*Bert Atari 2600 Seaquest Atari 2600 Venture Atari 2600 Space Invaders Atari 2600 Frostbite Atari 2600 Gravitar Atari 2600 Pong Atari 2600 Private Eye Atari 2600 Montezuma's Revenge Atari 2600 Alien

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	GDI-I3(200M frames)	Score	864	—	Unverified
2	GDI-H3(200M frames)	Score	864	—	Unverified
3	GDI-H3	Score	864	—	Unverified
4	GDI-I3	Score	864	—	Unverified
5	Bootstrapped DQN	Score	855	—	Unverified
6	FQF	Score	854.2	—	Unverified
7	R2D2	Score	837.7	—	Unverified
8	Ape-X	Score	800.9	—	Unverified
9	Agent57	Score	790.4	—	Unverified
10	IMPALA (deep)	Score	787.34	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	IQN	Score	34	—	Unverified
2	QR-DQN-1	Score	34	—	Unverified
3	TRPO-hash	Score	34	—	Unverified
4	NoisyNet-Dueling	Score	34	—	Unverified
5	GDI-H3	Score	34	—	Unverified
6	GDI-H3(200M frames)	Score	34	—	Unverified
7	GDI-I3	Score	34	—	Unverified
8	Go-Explore	Score	34	—	Unverified
9	Bootstrapped DQN	Score	33.9	—	Unverified
10	C51 noop	Score	33.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Agent57	Score	580,328.14	—	Unverified
2	QR-DQN-1	Score	572,510	—	Unverified
3	R2D2	Score	408,850	—	Unverified
4	IMPALA (deep)	Score	351,200.12	—	Unverified
5	Ape-X	Score	302,391.3	—	Unverified
6	A2C + SIL	Score	104,975.6	—	Unverified
7	MuZero (Res2 Adam)	Score	94,906.25	—	Unverified
8	DreamerV2	Score	94,688	—	Unverified
9	MuZero	Score	72,276	—	Unverified
10	DNA	Score	52,398	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GDI-H3	Score	1,000,000	—	Unverified
2	GDI-H3(200M frames)	Score	1,000,000	—	Unverified
3	Agent57	Score	999,997.63	—	Unverified
4	R2D2	Score	999,996.7	—	Unverified
5	MuZero	Score	999,976.52	—	Unverified
6	MuZero (Res2 Adam)	Score	999,659.18	—	Unverified
7	GDI-I3	Score	943,910	—	Unverified
8	Ape-X	Score	392,952.3	—	Unverified
9	C51 noop	Score	266,434	—	Unverified
10	Duel noop	Score	50,254.2	—	Unverified