Feature-based aggregation and deep reinforcement learning: a survey and some new implementations.
Dimitri P. BertsekasPublished in: IEEE CAA J. Autom. Sinica (2019)
Keyphrases
- reinforcement learning
- function approximation
- data aggregation
- multi agent
- multi agent reinforcement learning
- state space
- rank aggregation
- markov decision processes
- efficient implementation
- reinforcement learning algorithms
- model free
- direct policy search
- robotic control
- aggregation functions
- deep learning
- aggregation operators
- temporal difference
- databases
- image features
- decision making
- partially observable
- transfer learning
- optimal policy
- learning process
- autonomous learning
- database systems
- policy search
- relational reinforcement learning
- case study