MearcAll papers

arXiv 1312.5602 · cs.LG

Playing Atari with Deep Reinforcement Learning

Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and 1 more

Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.

No reproduction recordedclm_254a8c40
So far the network has outperformed all previous RL algorithms on six of the seven games we have attempted and surpassed an expert human player on three of them.

Introduction · page 2 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_40cc0f9f
Since this approach was able to outperform the best human backgammon players 20 years ago, it is natural to wonder whether two decades of hardware improvements, coupled with modern deep … (excerpt)

Deep Reinforcement Learning · page 4 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_a03aeb35
Note that our reported human scores are much higher than the ones in Bellemare et al. [3].

Main Evaluation · page 7 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_18743db3
Our approach (labeled DQN) outperforms the other learning methods by a substantial margin on all seven games despite incorporating almost no prior knowledge about the inputs.

Main Evaluation · page 7 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_86c195d2
Nevertheless, we show that on all the games, except Space Invaders, not only our max evaluation results (row 8), but also our average results (row 4) achieve better performance.

Main Evaluation · page 8 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_d2bdc5c8
Finally, we show that our method achieves better performance than an expert human player on Breakout, Enduro and Pong and it achieves close to human performance on Beam Rider.

Main Evaluation · page 8 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_81550baf
Our approach gave state-of-the-art results in six of the seven games it was tested on, with no adjustment of the architecture or hyperparameters.

Conclusion · page 8 · Automated extraction, not reviewed · 0 reviewed reproductions

Reproduced one of these claims?

Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1312.5602) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.