A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
IRIS introduces a Transformer-based world model that learns from pixels and achieves human-level performance on Atari 100k with high sample efficiency.
M. G. Bellemare, Y. Naddaf, J. Veness, et al.
Introduces the Arcade Learning Environment (ALE), a platform and methodology for evaluating general, domain-independent AI agents across hundreds of Atari 2600 games.
Unknown
This paper explores model-based reinforcement learning with stochastic predictive models as a promising, efficient alternative to model-free methods for Atari games.
Stefan Elfwing, Eiji Uchibe, Kenji Doya
This paper proposes SiLU and dSiLU activation functions and demonstrates that on-policy Sarsa(λ) with softmax action selection can outperform DQN in Atari games without experience replay or target networks.
Hado van Hasselt, Arthur Guez, David Silver
This paper shows that DQN overestimates action values in Atari games and proposes a Double DQN algorithm that reduces overestimation and improves performance.