Policy Synthesis and Reinforcement Learning for Discounted LTL.
Rajeev AlurOsbert BastaniKishor JothimuruganMateo PerezFabio SomenziAshutosh TrivediPublished in: CoRR (2023)
Keyphrases
- optimal policy
- reinforcement learning
- markov decision process
- markov decision processes
- infinite horizon
- average reward
- state space
- total reward
- finite horizon
- dynamic programming
- decision problems
- long run
- policy iteration
- function approximation
- state and action spaces
- finite state
- partially observable
- reinforcement learning algorithms
- policy search
- model free
- action space
- markov decision problems
- average cost
- temporal logic
- model checking
- action selection
- control policies
- state dependent
- linear temporal logic
- partially observable markov decision processes
- optimal control
- learning algorithm
- initial state
- reward function
- function approximators
- approximate dynamic programming
- reinforcement learning problems
- sufficient conditions
- bounded model checking
- discounted reward
- deterministic automata
- policy evaluation
- planning problems
- multi agent
- machine learning