Reinforcement Learning with Non-Markovian Rewards.
Maor GaonRonen I. BrafmanPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- reward function
- function approximation
- markov decision processes
- reinforcement learning algorithms
- state space
- optimal policy
- model free
- temporal difference
- machine learning
- hidden state
- multi agent
- reinforcement learning methods
- reinforcement learning agents
- reward shaping
- optimal control
- supervised learning
- partially observable
- multi agent reinforcement learning
- policy search
- transition probabilities
- action selection
- stochastic process
- autonomous learning
- robotic control