Deep reinforcement learning and imitation learning based on VizDoom.
Yingyu XuPublished in: EITCE (2022)
Keyphrases
- imitation learning
- reinforcement learning
- reinforcement learning methods
- temporal difference
- function approximation
- state space
- markov decision processes
- learning algorithm
- reinforcement learning algorithms
- multi agent
- machine learning
- learning problems
- multi modal
- optimal policy
- training samples
- evaluation function
- humanoid robot
- model free
- control strategies
- dynamic programming
- training set
- control problems
- hidden state