The Guiding Role of Reward Based on Phased Goal in Reinforcement Learning.
Yiming LiuZheng HuPublished in: ICMLC (2020)
Keyphrases
- reinforcement learning
- function approximation
- partially observable environments
- agent learns
- state space
- learning algorithm
- reinforcement learning algorithms
- temporal difference
- model free
- learning problems
- learning agent
- dynamic programming
- multi agent
- machine learning
- neural network
- optimal policy
- function approximators
- average reward
- eligibility traces
- markov decision processes
- database
- artificial intelligence
- policy search
- robotic control
- real time