Guided Soft Actor Critic: A Guided Deep Reinforcement Learning Approach for Partially Observable Markov Decision Processes.
Mehmet HaklidirHakan TemeltasPublished in: IEEE Access (2021)
Keyphrases
- actor critic
- reinforcement learning
- partially observable markov decision processes
- policy gradient
- temporal difference
- reinforcement learning algorithms
- optimal control
- approximate dynamic programming
- partially observable
- function approximation
- state space
- neuro fuzzy
- dynamic programming
- finite state
- optimal policy
- gradient method
- dynamical systems
- average reward
- policy gradient methods
- model free
- markov decision processes
- reinforcement learning methods
- machine learning
- infinite horizon
- planning problems
- rl algorithms
- markov chain
- multi agent