Oblivious Markov Decision Processes: Planning and Policy Execution.
Murtadha AlsayeghJose FuentesLeonardo BobadillaDylan A. ShellPublished in: CDC (2023)
Keyphrases
- markov decision processes
- optimal policy
- partially observable
- policy iteration
- macro actions
- markov decision process
- decision theoretic planning
- partially observable markov decision processes
- state space
- markov decision problems
- planning under uncertainty
- average reward
- infinite horizon
- reinforcement learning
- state and action spaces
- finite horizon
- plan generation
- finite state
- average cost
- dynamic programming
- reward function
- planning problems
- plan execution
- action space
- decision problems
- transition matrices
- total reward
- policy evaluation
- decision processes
- factored mdps
- reinforcement learning algorithms
- reachability analysis
- discounted reward
- long run
- probabilistic planning
- expected reward
- multistage
- action sets
- action selection
- stationary policies
- partially observable markov decision process
- model free
- ai planning
- model based reinforcement learning
- continuous state spaces
- initial state
- planning graph
- heuristic search
- classical planning