Recent Advances in Deep Reinforcement Learning Applications for Solving Partially Observable Markov Decision Processes (POMDP) Problems: Part 1 - Fundamentals and Applications in Games, Robotics and Natural Language Processing.
Xuanchen XiangSimon FooPublished in: Mach. Learn. Knowl. Extr. (2021)
Keyphrases
- partially observable markov decision processes
- recent advances
- reinforcement learning
- sequential decision making problems
- partial observability
- continuous state
- planning under uncertainty
- optimal policy
- finite state
- decision problems
- state space
- dynamical systems
- markov decision processes
- belief state
- belief space
- dynamic programming
- policy search
- dec pomdps
- partially observable stochastic games
- multi agent
- field of pattern recognition
- partially observable
- function approximation
- policy gradient
- fully observable
- partially observable domains
- partially observable markov decision process
- hidden state
- stochastic domains
- continuous state spaces
- planning problems
- partially observable markov decision
- machine learning
- learning algorithm
- markov decision problems
- approximate solutions
- policy evaluation
- reinforcement learning methods
- action space
- decision theoretic planning
- bayesian reinforcement learning
- model free reinforcement learning
- initial state
- reinforcement learning algorithms
- infinite horizon
- optimal control
- function approximators
- markov decision process
- markov chain
- multi agent systems