Distributional Reward Decomposition for Reinforcement Learning.
Zichuan LinLi ZhaoDerek YangTao QinGuangwen YangTie-Yan LiuPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- state space
- co occurrence
- reinforcement learning algorithms
- markov decision processes
- model free
- eligibility traces
- reward function
- robotic control
- image decomposition
- temporal difference
- action selection
- optimal control
- optimal policy
- learning agent
- temporal difference learning
- learning algorithm
- machine learning
- decomposition method
- decomposition algorithm
- reinforcement learning methods
- multi agent
- long run
- learning capabilities
- supervised learning
- hierarchical decomposition