Atari Games on Atari 2600 Atlantis

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	GDI-H3	3837300	No	Generalized Data Distribution Iteration	2022-06-07	-
2	GDI-I3	3803000	No	Generalized Data Distribution Iteration	2022-06-07	-
3	A2C + SIL	3084781.7	No	Self-Imitation Learning	2018-06-14	Code
4	POP3D	2193605.67	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
5	MuZero	1674767.2	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
6	R2D2	1620764	No	-	-	Code
7	Agent57	1528841.76	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
8	Persistent AL	1465250	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
9	ES FF (1 hour) noop	1267410	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
10	MuZero (Res2 Adam)	1137475.12	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
11	Bootstrapped DQN	994500	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
12	DreamerV2	978778	No	Mastering Atari with Discrete World Models	2020-10-05	Code
13	IQN	978200	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
14	NoisyNet-Dueling	972175	No	Noisy Networks for Exploration	2017-06-30	Code
15	QR-DQN-1	971850	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
16	ASL DDQN	947275	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
17	Ape-X	944497.5	No	Distributed Prioritized Experience Replay	2018-03-02	Code
18	DNA	932559	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
19	A3C FF hs	911091	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
20	A3C LSTM hs	875822	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
21	IMPALA (deep)	849967.5	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
22	C51 noop	841075	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
23	A3C FF (1 day) hs	772392	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
24	Gorila	629166.5	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
25	Advantage Learning	553591.67	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
26	Duel hs	445360	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
27	Prior+Duel hs	423252	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
28	Prior+Duel noop	395762	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
29	Duel noop	382572	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
30	Prior noop	357324	No	Prioritized Experience Replay	2015-11-18	Code
31	DDQN+Pop-Art noop	340076	No	Learning values across many orders of magnitude	2016-02-24	-
32	Prior hs	330647	No	Prioritized Experience Replay	2015-11-18	Code
33	DDQN (tuned) hs	319688	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
34	Reactor 500M	302831	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
35	DQN hs	292491	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
36	DQN noop	279987	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
37	UCT	193858	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
38	DDQN (tuned) noop	106056	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
39	CGP	99240	No	Evolving simple programs for playing Atari games	2018-06-14	Code
40	Nature DQN	85641	No	-	-	Code
41	Best Learner	62687	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
42	SARSA	852.9	No	-	-	-