Cyclophobic Reinforcement Learning.
Stefan Sylvius WagnerPeter ArndtJan RobineStefan HarmelingPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- machine learning
- control problems
- multi agent
- temporal difference
- robotic control
- real world
- relational reinforcement learning
- direct policy search
- database
- multi agent reinforcement learning
- temporal difference learning
- function approximators
- semi supervised
- transfer learning
- markov chain
- dynamic programming
- expert systems
- information systems
- social networks
- learning algorithm
- neural network
- data sets