Distributional Reinforcement Learning with Monotonic Splines.
Yudong LuoGuiliang LiuHaonan DuanOliver SchultePascal PoupartPublished in: ICLR (2022)
Keyphrases
- reinforcement learning
- function approximation
- co occurrence
- closed form
- markov decision processes
- state space
- model free
- shape preserving
- temporal difference
- learning process
- control problems
- policy search
- transfer learning
- database
- b spline
- reinforcement learning algorithms
- learning agents
- transition model
- optimal policy
- multi agent
- social networks
- learning algorithm
- machine learning
- real world
- robotic control
- direct policy search
- cubic spline
- learning problems
- knowledge base
- data sets
- real time