Optimal Route Synthesis in Space DTN Using Markov Decision Processes.
Pedro R. D'ArgenioPublished in: ICTAC (2023)
Keyphrases
- markov decision processes
- dynamic programming
- average cost
- action space
- average reward
- finite horizon
- action sets
- state space
- finite state
- reinforcement learning
- total reward
- optimal policy
- discounted reward
- transition matrices
- reinforcement learning algorithms
- partially observable
- policy iteration
- decision theoretic planning
- risk sensitive
- infinite horizon
- planning under uncertainty
- state and action spaces
- decision processes
- search space
- stationary policies
- optimal control
- reward function
- reachability analysis
- least squares
- continuous state spaces
- machine learning
- model based reinforcement learning
- np hard
- markov chain
- long run
- sufficient conditions