Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer.
Edward BeechingChristian WolfJilles DibangoyeOlivier SimoninPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- control problems
- optimal control
- control policy
- control system
- automated reasoning
- control method
- control strategy
- robotic control
- robot control
- knowledge base
- state space
- building blocks
- data acquisition
- real time
- function approximation
- knowledge representation
- dynamic programming
- adaptive control
- control strategies
- expert systems
- massively parallel
- learning process
- reasoning process
- multi agent
- learning algorithm