Robust Reinforcement Learning via Progressive Task Sequence.
Yike LiYunzhe TianEndong TongWenjia NiuJiqiang LiuPublished in: IJCAI (2023)
Keyphrases
- reinforcement learning
- function approximation
- robust estimation
- long sequences
- machine learning
- multi agent
- markov decision processes
- computationally efficient
- learning process
- hidden state
- reinforcement learning algorithms
- model free
- partial occlusion
- dynamic programming
- evolutionary algorithm
- data sets
- pairwise
- multiscale
- computer vision
- learning algorithm
- information retrieval
- data mining
- real world
- neural network