Autoregressive Policies for Continuous Control Deep Reinforcement Learning.
Dmytro KorenkevychA. Rupam MahmoodGautham VasanJames BergstraPublished in: CoRR (2019)
Keyphrases
- autoregressive
- reinforcement learning
- control policies
- control policy
- optimal policy
- action space
- gaussian markov random field
- moving average
- non stationary
- random fields
- fitted q iteration
- autoregressive model
- optimal control
- markov decision process
- machine learning
- autoregressive moving average
- policy search
- spectrum analysis
- action selection
- dynamic programming
- computer vision
- state space
- information retrieval