A Nonlinear Approach to Robust Routing Based on Reinforcement Learning with State Space Compression and Adaptive Basis Construction.
Hideki SatohPublished in: IEICE Trans. Fundam. Electron. Commun. Comput. Sci. (2008)
Keyphrases
- state space
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- heuristic search
- optimal policy
- dynamical systems
- routing problem
- dynamic programming
- data compression
- function approximation
- temporal difference
- adaptive control
- markov decision process
- routing protocol
- action space
- machine learning
- control problems
- learning agent
- continuous state
- network topology
- optimal control
- compression ratio
- particle filter
- peer to peer
- learning process
- search space
- multi agent