Birs- 14w5077: Optimal Cooperation, Communication, and Learning in Decentralized Systems
-
Title: Online learning in Markov Decision Processes with changing reward sequences
Speaker:
Link:
-
Title: Online learning under delayed feedback
Speaker:
Link:
-
Title: Blackwell approachability in (stochastic) games
Speaker:
Link:
-
Title: Quantization for stabilization, optimization and approximation in networked control
Speaker:
Link:
-
Title: Information theory and decentralized control
Speaker:
Link:
-
Title: On myopic strategies in dynamic adversarial team decision problems
Speaker:
Link:
-
Title: Information constraints in distributed and online learning
Speaker:
Link:
-
Title: Gossip and related algorithms
Speaker:
Link: