Reinforcement Learning for Omega-Regular Specifications on Continuous-Time MDP.
Amin FalahShibashis GuhaAshutosh TrivediPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- state space
- markov decision processes
- markov decision process
- optimal policy
- optimal control
- semi markov decision process
- markov chain
- reinforcement learning algorithms
- reward function
- state and action spaces
- action sets
- function approximation
- partially observable
- action space
- model free
- stationary policies
- heuristic search
- state abstraction
- high level
- machine learning
- average reward
- markov decision problems
- dynamic programming
- policy iteration
- continuous state spaces
- multi agent
- delay insensitive
- factored markov decision processes
- inverse reinforcement learning
- policy search
- approximate dynamic programming
- dynamical systems
- action selection
- formal specification
- finite state
- learning process
- reward shaping
- continuous state
- reinforcement learning methods
- state action
- markov processes
- learning problems
- planning problems
- infinite horizon