Recent Advances in Deep Reinforcement Learning Applications for Solving Partially Observable Markov Decision Processes (POMDP) Problems Part 2 - Applications in Transportation, Industries, Communications and Networking and More Topics.
Xuanchen XiangSimon Y. FooHuanyu ZangPublished in: Mach. Learn. Knowl. Extr. (2021)
Keyphrases
- partially observable markov decision processes
- recent advances
- reinforcement learning
- sequential decision making problems
- continuous state
- optimal policy
- partial observability
- planning under uncertainty
- finite state
- decision problems
- markov decision processes
- dynamical systems
- state space
- dynamic programming
- partially observable environments
- belief state
- belief space
- hidden state
- partially observable markov decision process
- partially observable
- function approximation
- dec pomdps
- partially observable domains
- continuous state spaces
- partially observable stochastic games
- markov decision process
- reinforcement learning algorithms
- stochastic domains
- average reward
- decision theoretic planning
- multi agent
- fully observable
- field of pattern recognition
- partially observable markov decision
- policy evaluation
- reinforcement learning methods
- approximate solutions
- model free
- planning problems
- learning algorithm
- machine learning
- policy gradient
- action space
- temporal difference
- decision theoretic
- domain specific
- model free reinforcement learning