Search-based Reinforcement Learning through Bandit Linear Optimization.
Milan PeelmanAntoon BronselaerGuy De TréPublished in: IJCAI (2022)
Keyphrases
- reinforcement learning
- search algorithm
- optimization algorithm
- markov decision processes
- machine learning
- constrained optimization
- global search
- multi agent
- semidefinite
- optimization problems
- search strategy
- search strategies
- function approximation
- search efficiency
- search methods
- highly non linear
- fine tuning
- information retrieval systems
- learning algorithm