Automatic Exploration Process Adjustment for Safe Reinforcement Learning with Joint Chance Constraint Satisfaction.
Yoshihiro OkawaTomotake SasakiHidenao IwanePublished in: CoRR (2021)
Keyphrases
- constraint satisfaction
- constraint satisfaction problems
- reinforcement learning
- heuristic search
- constraint programming
- relaxation labeling
- constraint propagation
- markov decision processes
- phase transition
- sat solvers
- combinatorial problems
- robust fault detection
- constraint relaxation
- arc consistency
- action selection
- function approximation
- constraint solving
- product configuration
- orders of magnitude
- state space