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 151–175 of 625 papers

Title	Date	Tasks	Status	Hype
Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks	Mar 31, 2022	Atari GamesDeep Reinforcement Learning	—Unverified	0
Learning Relational Rules from Rewards	Mar 25, 2022	Atari Games	CodeCode Available	0
NavDreams: Towards Camera-Only RL Navigation Among Humans	Mar 23, 2022	Atari GamesNavigate	CodeCode Available	1
Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act	Mar 16, 2022	Atari GamesDecision Making	—Unverified	0
Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise	Mar 2, 2022	Atari GamesDiversity	—Unverified	0
On the Generalization of Representations in Reinforcement Learning	Mar 1, 2022	Atari Gamesreinforcement-learning	CodeCode Available	0
A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search	Feb 11, 2022	Atari GamesDecision Making	—Unverified	0
ExPoSe: Combining State-Based Exploration with Gradient-Based Online Search	Feb 3, 2022	Atari GamesDecision Making	CodeCode Available	0
Distributional Reinforcement Learning with Regularized Wasserstein Loss	Feb 1, 2022	Atari GamesDistributional Reinforcement Learning	CodeCode Available	0
Deep Reinforcement Learning with Spiking Q-learning	Jan 21, 2022	Atari GamesDeep Reinforcement Learning	—Unverified	0
Exploration by Random Network Distillation	Jan 17, 2022	Atari GamesDeep Reinforcement Learning	—Unverified	0
Attention Option-Critic	Jan 7, 2022	Atari GamesTransfer Learning	—Unverified	0
Execute Order 66: Targeted Data Poisoning for Reinforcement Learning	Jan 3, 2022	Atari GamesData Poisoning	—Unverified	0
A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning	Dec 31, 2021	Atari GamesMeta Reinforcement Learning	CodeCode Available	0
Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs	Dec 16, 2021	Atari GamesDeep Reinforcement Learning	—Unverified	0
Conjugated Discrete Distributions for Distributional Reinforcement Learning	Dec 14, 2021	Atari GamesDistributional Reinforcement Learning	CodeCode Available	0
Human-Level Control through Directly-Trained Deep Spiking Q-Networks	Dec 13, 2021	Atari Gamesreinforcement-learning	CodeCode Available	1
Continual Learning In Environments With Polynomial Mixing Times	Dec 13, 2021	Atari GamesContinual Learning	CodeCode Available	0
A Benchmark for Low-Switching-Cost Reinforcement Learning	Dec 13, 2021	Atari Gamesreinforcement-learning	—Unverified	0
DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization	Dec 9, 2021	Atari GamesD4RL	—Unverified	0
A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutions	Dec 8, 2021	Atari GamesDeep Reinforcement Learning	—Unverified	0
Hybrid Self-Attention NEAT: A novel evolutionary approach to improve the NEAT algorithm	Dec 7, 2021	Atari GamesEvolutionary Algorithms	CodeCode Available	1
Virtual Replay Cache	Dec 6, 2021	Atari GamesDeep Reinforcement Learning	CodeCode Available	0
Target Entropy Annealing for Discrete Soft Actor-Critic	Dec 6, 2021	Atari GamesScheduling	—Unverified	0
NovelD: A Simple yet Effective Exploration Criterion	Dec 1, 2021	Atari GamesDeep Reinforcement Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 7 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-H3(200M frames)	Score	864	—	Unverified
2	GDI-H3	Score	864	—	Unverified
3	GDI-I3(200M frames)	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	GDI-I3	Score	34	—	Unverified
2	NoisyNet-Dueling	Score	34	—	Unverified
3	GDI-H3	Score	34	—	Unverified
4	TRPO-hash	Score	34	—	Unverified
5	IQN	Score	34	—	Unverified
6	QR-DQN-1	Score	34	—	Unverified
7	GDI-H3(200M frames)	Score	34	—	Unverified
8	Go-Explore	Score	34	—	Unverified
9	ASL DDQN	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(200M frames)	Score	1,000,000	—	Unverified
2	GDI-H3	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