Structured Reward Shaping using Signal Temporal Logic specifications.
Anand BalakrishnanJyotirmoy V. DeshmukhPublished in: IROS (2019)
Keyphrases
- temporal logic
- concurrent systems
- model checking
- reward shaping
- transition systems
- model checker
- bounded model checking
- reactive systems
- formal specification language
- formal specification
- modal logic
- reinforcement learning
- complex domains
- formal verification
- computation tree logic
- finite state
- verification method
- linear temporal logic
- domain specific
- computational complexity
- control flow
- knowledge base
- expert systems
- bayesian networks