Distributional Meta-Gradient Reinforcement Learning.
Haiyan YinShuicheng YanZhongwen XuPublished in: ICLR (2023)
Keyphrases
- reinforcement learning
- policy gradient
- function approximation
- model free
- meta level
- optimal control
- co occurrence
- learning problems
- markov decision processes
- edge detection
- meta reasoning
- real time
- supervised learning
- state space
- learning process
- multi agent systems
- multi agent
- dynamic programming
- domain knowledge
- temporal difference
- robot control
- image processing
- multi agent reinforcement learning
- policy search
- data mining