Reinforcement Learning with Non-Markovian Rewards.
Maor GaonRonen I. BrafmanPublished in: AAAI (2020)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- reward function
- state space
- optimal policy
- reinforcement learning algorithms
- learning algorithm
- temporal difference
- supervised learning
- multi agent
- reinforcement learning agents
- hidden state
- partially observable
- optimal control
- machine learning
- dynamic programming
- action space
- markov decision problems
- learning process
- reward shaping
- action selection
- model free
- learning problems
- transfer learning
- reinforcement learning methods