RL-DARTS: Differentiable Architecture Search for Reinforcement Learning.
Yingjie MiaoXingyou SongDaiyi PengSummer YueEugene BrevdoAleksandra FaustPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- search algorithm
- state space
- model free
- reinforcement learning algorithms
- markov decision processes
- multi agent
- objective function
- search mechanism
- management system
- learning algorithm
- machine learning
- search space
- optimal policy
- control problems
- neural network
- optimal control
- direct policy search
- temporal difference learning
- search strategy
- dynamic programming
- temporal difference
- transfer learning
- markov decision process
- learning agents
- supervised learning
- partially observable domains
- information retrieval