clm_254a8c40So 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.
arXiv 1312.5602 · cs.LG
Read on arXiv · arXiv non-exclusive license
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.
clm_254a8c40So 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.
res_40cc0f9fSince 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)
res_a03aeb35Note that our reported human scores are much higher than the ones in Bellemare et al. [3].
clm_18743db3Our 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.
res_86c195d2Nevertheless, 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.
clm_d2bdc5c8Finally, 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.
clm_81550bafOur 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.
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.