paper-with-me

Atari Games 벤치마크

Atari Games on atari game

18개 결과 · ⬇ CSV · JSON

Human World Record Breakthrough

4 8.5 13 17.5 22 2017-10 2026-09 Rainbow — 4.0 (2017-10-06) Rainbow — 4.0 (2017-10-06) Go-Explore — 17.0 (2019-01-30) Go-Explore — 17.0 (2019-01-30) R2D2 — 15.0 (2019-05-01) R2D2 — 15.0 (2019-05-01) Muzero — 19.0 (2019-11-19) Muzero — 19.0 (2019-11-19) NGU — 8.0 (2020-02-14) NGU — 8.0 (2020-02-14) Agent57 — 18.0 (2020-03-30) Agent57 — 18.0 (2020-03-30) Muesli — 5.0 (2021-04-13) Muesli — 5.0 (2021-04-13) GDI-H3 — 22.0 (2022-06-07) GDI-I3 — 17.0 (2022-06-07) GDI-H3 — 22.0 (2022-06-07) GDI-I3 — 17.0 (2022-06-07) Rainbow — 4.0 (2017-10-06) Go-Explore — 17.0 (2019-01-30) Muzero — 19.0 (2019-11-19) GDI-H3 — 22.0 (2022-06-07)
RankModel Human World Record Breakthrough PaperCodeYear
1 GDI-H3 22 Generalized Data Distribution Iteration 2022
2 Muzero 19 Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15 2019
3 Agent57 18 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2 2020
4 Go-Explore 17 Go-Explore: a New Approach for Hard-Exploration Problems uber-research/go-explore · Adeikalam/Go-Explore · Dorozhko-Anton/go-explore 2019
4 GDI-I3 17 Generalized Data Distribution Iteration 2022
6 R2D2 15 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl 2019
7 NGU 8 Never Give Up: Learning Directed Exploration Strategies opendilab/DI-engine · rle-foundation/rlexplore · michaelnny/deep_rl_zoo · +3 2020
8 Muesli 5 Muesli: Combining Improvements in Policy Optimization YuriCat/MuesliJupyterExample · Itomigna2/Muesli-lunarlander 2021
9 Rainbow 4 Rainbow: Combining Improvements in Deep Reinforcement Learning thu-ml/tianshou · facebookresearch/ReAgent · facebookresearch/Horizon · +31 2017
10 GDI-H3 22 Generalized Data Distribution Iteration 2022
11 Muzero 19 Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15 2019
12 Agent57 18 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2 2020
13 Go-Explore 17 Go-Explore: a New Approach for Hard-Exploration Problems uber-research/go-explore · Adeikalam/Go-Explore · Dorozhko-Anton/go-explore 2019
13 GDI-I3 17 Generalized Data Distribution Iteration 2022
15 R2D2 15 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl 2019
16 NGU 8 Never Give Up: Learning Directed Exploration Strategies opendilab/DI-engine · rle-foundation/rlexplore · michaelnny/deep_rl_zoo · +3 2020
17 Muesli 5 Muesli: Combining Improvements in Policy Optimization YuriCat/MuesliJupyterExample · Itomigna2/Muesli-lunarlander 2021
18 Rainbow 4 Rainbow: Combining Improvements in Deep Reinforcement Learning thu-ml/tianshou · facebookresearch/ReAgent · facebookresearch/Horizon · +31 2017
1–18 / 18 페이지당 10 20 50 100