Atari Games on Atari 2600 Tennis

Metric: Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Sort:

#	Model↕	Score▼	Extra Data	Paper	Date↕	Code
1	GDI-I3	24	No	Generalized Data Distribution Iteration	2022-06-07	-
2	GDI-I3	24	No	Generalized Data Distribution Iteration	2022-06-07	-
3	GDI-H3	24	No	Generalized Data Distribution Iteration	2022-06-07	-
4	Ape-X	23.9	No	Distributed Prioritized Experience Replay	2018-03-02	Code
5	Agent57	23.84	No	Agent57: Outperforming the Atari Human Benchmark	2020-03-30	Code
6	IQN	23.6	No	Implicit Quantile Networks for Distributional Re...	2018-06-14	Code
7	QR-DQN-1	23.6	No	Distributional Reinforcement Learning with Quant...	2017-10-27	Code
8	C51 noop	23.1	No	A Distributional Perspective on Reinforcement Le...	2017-07-21	Code
9	ASL DDQN	22.3	No	Train a Real-world Local Path Planner in One Hou...	2023-05-07	Code
10	Recurrent Rational DQN Average	20.6	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
11	Rational DQN Average	20.5	No	Adaptive Rational Activations to Boost Deep Rein...	2021-02-18	Code
12	DreamerV2	14	No	Mastering Atari with Discrete World Models	2020-10-05	Code
13	DQN noop	12.2	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
14	DDQN+Pop-Art noop	12.1	No	Learning values across many orders of magnitude	2016-02-24	-
15	DQN hs	11.1	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
16	Duel noop	5.1	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
17	Duel hs	4.4	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code
18	UCT	2.8	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
19	IMPALA (deep)	0.55	No	IMPALA: Scalable Distributed Deep-RL with Import...	2018-02-05	Code
20	SARSA	0	No	-	-	-
21	Prior noop	0	No	-	-	Code
22	Prior+Duel noop	0	No	-	-	Code
23	Bootstrapped DQN	0	No	-	-	Code
24	MuZero	0	No	-	-	Code
25	CGP	0	No	-	-	Code
26	NoisyNet-Dueling	0	No	-	-	Code
27	Advantage Learning	0	No	-	-	Code
28	MuZero (Res2 Adam)	0	No	-	-	Code
29	R2D2	-0.1	No	-	-	Code
30	Best Learner	-0.1	No	The Arcade Learning Environment: An Evaluation P...	2012-07-19	Code
31	Gorila	-0.7	No	Massively Parallel Methods for Deep Reinforcemen...	2015-07-15	Code
32	Nature DQN	-2.5	No	-	-	Code
33	ES FF (1 hour) noop	-4.5	No	Evolution Strategies as a Scalable Alternative t...	2017-03-10	Code
34	Prior hs	-5.3	No	Prioritized Experience Replay	2015-11-18	Code
35	A3C FF hs	-6.3	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
36	A3C LSTM hs	-6.4	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
37	DDQN (tuned) hs	-7.8	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
38	POP3D	-8.32	No	Policy Optimization With Penalized Point Probabi...	2018-07-02	Code
39	A3C FF (1 day) hs	-10.2	No	Asynchronous Methods for Deep Reinforcement Lear...	2016-02-04	Code
40	DNA	-10.9	No	DNA: Proximal Policy Optimization with a Dual Ne...	2022-06-20	Code
41	Prior+Duel hs	-13.2	No	Deep Reinforcement Learning with Double Q-learning	2015-09-22	Code
42	A2C + SIL	-17.3	No	Self-Imitation Learning	2018-06-14	Code
43	DDQN (tuned) noop	-22.8	No	Dueling Network Architectures for Deep Reinforce...	2015-11-20	Code

#1GDI-I3SOTA
24
Score· 2022-06-07
Generalized Data Distribution Iteration
#2GDI-I3
24
Score· 2022-06-07
Generalized Data Distribution Iteration
#3GDI-H3
24
Score· 2022-06-07
Generalized Data Distribution Iteration
#4Ape-XSOTA
23.9
Score· 2018-03-02
Distributed Prioritized Experience Replay Code
#5Agent57
23.84
Score· 2020-03-30
Agent57: Outperforming the Atari Human Benchmark Code
#6IQN
23.6
Score· 2018-06-14
Implicit Quantile Networks for Distributional Reinforcement Learning Code
#7QR-DQN-1SOTA
23.6
Score· 2017-10-27
Distributional Reinforcement Learning with Quantile Regression Code
#8C51 noopSOTA
23.1
Score· 2017-07-21
A Distributional Perspective on Reinforcement Learning Code
#9ASL DDQN
22.3
Score· 2023-05-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity Code
#10Recurrent Rational DQN Average
20.6
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#11Rational DQN Average
20.5
Score· 2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning Code
#12DreamerV2
14
Score· 2020-10-05
Mastering Atari with Discrete World Models Code
#13DQN noopSOTA
12.2
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#14DDQN+Pop-Art noop
12.1
Score· 2016-02-24
Learning values across many orders of magnitude
#15DQN hs
11.1
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#16Duel noop
5.1
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#17Duel hs
4.4
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code
#18UCTSOTA
2.8
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#19IMPALA (deep)
0.55
Score· 2018-02-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures Code
#20SARSA
0
Score
No paper
#21Prior noop
0
Score
No paperCode
#22Prior+Duel noop
0
Score
No paperCode
#23Bootstrapped DQN
0
Score
No paperCode
#24MuZero
0
Score
No paperCode
#25CGP
0
Score
No paperCode
#26NoisyNet-Dueling
0
Score
No paperCode
#27Advantage Learning
0
Score
No paperCode
#28MuZero (Res2 Adam)
0
Score
No paperCode
#29R2D2
-0.1
Score
No paperCode
#30Best Learner
-0.1
Score· 2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents Code
#31Gorila
-0.7
Score· 2015-07-15
Massively Parallel Methods for Deep Reinforcement Learning Code
#32Nature DQN
-2.5
Score
No paperCode
#33ES FF (1 hour) noop
-4.5
Score· 2017-03-10
Evolution Strategies as a Scalable Alternative to Reinforcement Learning Code
#34Prior hs
-5.3
Score· 2015-11-18
Prioritized Experience Replay Code
#35A3C FF hs
-6.3
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#36A3C LSTM hs
-6.4
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#37DDQN (tuned) hs
-7.8
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#38POP3D
-8.32
Score· 2018-07-02
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization Code
#39A3C FF (1 day) hs
-10.2
Score· 2016-02-04
Asynchronous Methods for Deep Reinforcement Learning Code
#40DNA
-10.9
Score· 2022-06-20
DNA: Proximal Policy Optimization with a Dual Network Architecture Code
#41Prior+Duel hs
-13.2
Score· 2015-09-22
Deep Reinforcement Learning with Double Q-learning Code
#42A2C + SIL
-17.3
Score· 2018-06-14
Self-Imitation Learning Code
#43DDQN (tuned) noop
-22.8
Score· 2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning Code