Video Games on Atari 2600 Assault

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	MuZero	143972.03	No	Mastering Atari, Go, Chess and Shogi by Planning...	2019-11-19	Code
2	R2D2	108197	No	-	-	Code
3	GDI-H3	97155	No	Generalized Data Distribution Iteration	2022-06-07	-
4	Agent57	67212.67	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
5	GDI-I3	63876	No	Generalized Data Distribution Iteration	2022-06-07	-
6	MuZero (Res2 Adam)	33292.22	No	Online and Offline Reinforcement Learning by Pla...	2021-04-13	Code
7	IQN	29091	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
8	Ape-X	24559.4	No	Distributed Prioritized Experience Replay	2018-03-02	Code
9	DreamerV2	23625	No	Mastering Atari with Discrete World Models	2020-10-05	Code
10	QR-DQN-1	22012	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
11	IMPALA (deep)	19148.47	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
12	DNA	16293	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
13	A3C LSTM hs	14497.9	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
14	ASL DDQN	14372.8	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
15	Prior+Duel noop	11477	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
16	NoisyNet-Dueling	11231	No	Noisy Networks for Exploration	2017-06-30	Code
17	Prior+Duel hs	10950.6	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
18	Prior+Duel hs	10950.6	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
19	DDQN+Pop-Art noop	9011.6	No	Learning values across many orders of magnitude	2016-02-24	-
20	Reactor 500M	8323.3	No	The Reactor: A fast and sample-efficient Actor-C...	2017-04-15	-
21	Bootstrapped DQN	8047.1	No	Deep Exploration via Bootstrapped DQN	2016-02-15	Code
22	Prior noop	7672.1	No	Prioritized Experience Replay	2015-11-18	Code
23	C51 noop	7203	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
24	Prior hs	6548.9	No	Prioritized Experience Replay	2015-11-18	Code
25	DDQN (tuned) hs	6060.8	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
26	A3C FF hs	5474.9	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
27	POP3D	5400.13	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
28	DDQN (tuned) noop	5393.2	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
29	Duel noop	4621	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
30	DQN noop	4280.4	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
31	Duel hs	3994.8	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
32	A3C FF (1 day) hs	3746.1	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
33	Advantage Learning	3661.51	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
34	DQN hs	3489.3	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
35	Nature DQN	3359	No	-	-	Code
36	Persistent AL	3304.33	No	Increasing the Action Gap: New Operators for Rei...	2015-12-15	Code
37	A2C + SIL	1812	No	Self-Imitation Learning	2018-06-14	Code
38	ES FF (1 hour) noop	1673.9	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
39	UCT	1512.2	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
40	Gorila	1195.8	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
41	CGP	890.4	No	Evolving simple programs for playing Atari games	2018-06-14	Code
42	Best Learner	628	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
43	CURL	543.7	No	CURL: Contrastive Unsupervised Representations f...	2020-04-08	Code
44	SARSA	537	No	-	-	-
45	SAC	350	No	Soft Actor-Critic for Discrete Action Settings	2019-10-16	Code