Formal Multi-Objective Synthesis of Continuous-State MDPs.
Sofie HaesaertPetter NilssonSadegh SoudjaniPublished in: ACC (2021)
Keyphrases
- continuous state
- multi objective
- reinforcement learning
- continuous state and action spaces
- policy search
- action space
- markov decision processes
- finite state
- continuous state spaces
- evolutionary algorithm
- state space
- partially observable markov decision processes
- robot navigation
- state dependent
- optimal policy
- planning problems
- objective function
- control policies
- function approximation
- genetic algorithm
- markov decision problems
- continuous action
- action selection
- reinforcement learning algorithms
- real valued
- learning algorithm
- dynamic programming
- markov chain
- finite horizon
- policy iteration
- average reward
- neural network
- model free
- multi agent
- steady state
- stochastic processes
- average cost
- reward function