TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Playing Games/Atari Games/Atari 2600 Amidar

Atari Games on Atari 2600 Amidar

Metric: Score (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Score▼Extra DataPaperDate↕Code
1Agent5729660.08NoAgent57: Outperforming the Atari Human Benchmark2020-03-30Code
2R2D229321.4No--Code
3MuZero28634.39NoMastering Atari, Go, Chess and Shogi by Planning...2019-11-19Code
4Ape-X8659.2NoDistributed Prioritized Experience Replay2018-03-02Code
5NoisyNet-Dueling3537NoNoisy Networks for Exploration2017-06-30Code
6FQF3165.3NoFully Parameterized Quantile Function for Distri...2019-11-05Code
7IQN2946NoImplicit Quantile Networks for Distributional Re...2018-06-14Code
8DreamerV22577NoMastering Atari with Discrete World Models2020-10-05Code
9Duel noop2354.5NoDueling Network Architectures for Deep Reinforce...2015-11-20Code
10Prior+Duel noop2296.8NoDueling Network Architectures for Deep Reinforce...2015-11-20Code
11ASL DDQN2232.3NoTrain a Real-world Local Path Planner in One Hou...2023-05-07Code
12Prior noop1838.9NoPrioritized Experience Replay2015-11-18Code
13DDQN (tuned) noop1793.3NoDueling Network Architectures for Deep Reinforce...2015-11-20Code
14C51 noop1735NoA Distributional Perspective on Reinforcement Le...2017-07-21Code
15QR-DQN-11641NoDistributional Reinforcement Learning with Quant...2017-10-27Code
16Advantage Learning1557.43NoIncreasing the Action Gap: New Operators for Rei...2015-12-15Code
17IMPALA (deep)1554.79NoIMPALA: Scalable Distributed Deep-RL with Import...2018-02-05Code
18Persistent AL1451.65NoIncreasing the Action Gap: New Operators for Rei...2015-12-15Code
19GDI-I31442NoGeneralized Data Distribution Iteration2022-06-07-
20A2C + SIL1362NoSelf-Imitation Learning2018-06-14Code
21Bootstrapped DQN1272.5NoDeep Exploration via Bootstrapped DQN2016-02-15Code
22MuZero (Res2 Adam)1197.38NoOnline and Offline Reinforcement Learning by Pla...2021-04-13Code
23GDI-H31065NoGeneralized Data Distribution Iteration2022-06-07-
24DNA1025NoDNA: Proximal Policy Optimization with a Dual Ne...2022-06-20Code
25Reactor 500M1015.8NoThe Reactor: A fast and sample-efficient Actor-C...2017-04-15-
26DQN noop978NoDeep Reinforcement Learning with Double Q-learning2015-09-22Code
27DDQN+Pop-Art noop782.5NoLearning values across many orders of magnitude2016-02-24-
28Nature DQN739.5No--Code
29POP3D729.15NoPolicy Optimization With Penalized Point Probabi...2018-07-02Code
30VPN641NoValue Prediction Network2017-07-11Code
31A3C FF (1 day) hs283.9NoAsynchronous Methods for Deep Reinforcement Lear...2016-02-04Code
32A3C FF hs263.9NoAsynchronous Methods for Deep Reinforcement Lear...2016-02-04Code
33Rainbow+SEER250.5NoImproving Computational Efficiency in Visual Rei...2021-03-04Code
34Prior+Duel hs238.4NoDueling Network Architectures for Deep Reinforce...2015-11-20Code
35Prior+Duel hs238.4NoDueling Network Architectures for Deep Reinforce...2015-11-20Code
36CURL232.3NoCURL: Contrastive Unsupervised Representations f...2020-04-08Code
37CGP199NoEvolving simple programs for playing Atari games2018-06-14Code
38Gorila189.2NoMassively Parallel Methods for Deep Reinforcemen...2015-07-15Code
39SARSA183.6No---
40UCT180.3NoThe Arcade Learning Environment: An Evaluation P...2012-07-19Code
41DQN hs178.4NoDeep Reinforcement Learning with Double Q-learning2015-09-22Code
42A3C LSTM hs173NoAsynchronous Methods for Deep Reinforcement Lear...2016-02-04Code
43Duel hs172.7NoDueling Network Architectures for Deep Reinforce...2015-11-20Code
44DDQN (tuned) hs169.1NoDeep Reinforcement Learning with Double Q-learning2015-09-22Code
45Prior hs129.1NoPrioritized Experience Replay2015-11-18Code
46ES FF (1 hour) noop112NoEvolution Strategies as a Scalable Alternative t...2017-03-10Code
47Best Learner103.4NoThe Arcade Learning Environment: An Evaluation P...2012-07-19Code
48SAC7.9NoSoft Actor-Critic for Discrete Action Settings2019-10-16Code