Model-Free Reinforcement Learning for Optimal Control of Markov Decision Processes Under Signal Temporal Logic Specifications.
Krishna Chaitanya KalagarlaRahul JainPierluigi NuzzoPublished in: CDC (2021)
Keyphrases
- temporal logic
- optimal control
- markov decision processes
- dynamic programming
- reinforcement learning
- risk sensitive
- policy gradient
- model checking
- infinite horizon
- policy iteration
- average cost
- control problems
- state space
- finite state
- reinforcement learning algorithms
- optimal policy
- finite horizon
- belief revision
- action space
- function approximation
- partially observable
- planning under uncertainty
- average reward
- markov decision problems
- decision theoretic planning
- markov decision process
- control strategy
- multi agent
- reward function
- computational complexity
- learning algorithm
- data mining