Lukasz Stafiniak pages | AGI / AGI | browse. Overall course focus: (hmm…) Reinforcement learning. Concept formation and program synthesis. Adaptive and probabilistic logics. Mental development theory. Notes: Universal Artificial Intelligence: universal induction, exhaustive program search and reinforcement learning algorithms Δ ( TeXmacs source Δ ) A glimpse on Warren Smith’s idea of IQ test Δ ( source Δ ) Techniques of Reinforcement Learning Δ ( TeXmacs source Δ ) RL_Ch6_Evolutionary_modular.pdf Δ RL_Ch7_Hierarchical_RL.pdf Δ General Game Playing Δ ( TeXmacs source Δ ) Knowledge Representation and Language Δ ( TeXmacs source Δ ) Multi-layered Semantic Networks Δ (replaces a subchapter above) Ontological Semantics Δ Automated Language Acquisition Δ Adaptive and Probabilistic Logics for Reasoning Systems Adaptive (or Defeasible) Logics and OSCAR Δ (TODO: complete the notes about OSCAR) Frequency and/or Uncertainty Logics: Non Axiomatic Logic, Markov Logic Networks Δ , Probabilistic Logic Networks (to come) Inductive (Logic) Programming Considered: Ai.
Association for Uncertainty in Artificial Intelligence. Journal of AGI > Home. AI. Tag list. Peter Norvig.