A General Method For Incremental Self-Improvement And Multi-Agent Learning In Unrestricted Environme

By J. Urgen Schmidhuber. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Khimya Khetarpal
2. Matthew Riemer
3. Irina Rish
4. Doina Precup
5. Jian Zhao
6. J. Urgen Schmidhuber
7. Sergey Levine
8. A. Mahmood

Citations in the corpus

• Towards Continual Reinforcement Learning: A Review and Perspectives (2020, methodology): “SSA was also successfully applied to handle more complex multi-agent learning settings (Schmidhuber, 1999).”
• Artificial curiosity based on discovering novel algorithmic predictability through coevolution (1999, background): “(See [18] for a related gure illustrating how instruction sequences can be drawn from a probabilistic policy.”
• Incremental self-improvement for life-time multi-agent reinforcement learning (1996, methodology): “The method is based on two complementary kinds of processes: pushing and checking (Schmidhuber, 1994, 1995a, 1996a, b).”
• Probabilistic Incremental Program Evolution: Stochastic Search Through Program Space (1997, unknown): “Probabilistic Incremental Program Evolution:Stochastic Search Through Program SpaceRafa l Sa lustowicz and J urgen SchmidhuberIDSIA, Corso Elvezia 36, 6900 Lugano, Switzerlande-mail: frafal, juergeng@idsia.chtel.”