Feedback-Based Tree Search for Reinforcement Learning.
Daniel R. JiangEmmanuel EkwedikeHan LiuPublished in: ICML (2018)
Keyphrases
- tree search
- reinforcement learning
- state space
- search algorithm
- branch and bound
- constraint propagation
- game tree search
- mathematical programming
- search tree
- depth first search
- iterative deepening
- alpha beta
- search space
- heuristic search
- tree search algorithm
- orders of magnitude
- relevance feedback
- special case
- path finding
- game tree
- database systems
- learning algorithm
- branch and bound algorithm
- convergence rate
- tabu search
- video sequences
- machine learning