Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer.
Edward BeechingJilles DibangoyeOlivier SimoninChristian WolfPublished in: ICPR (2020)
Keyphrases
- reinforcement learning
- control problems
- robot control
- control system
- optimal control
- building blocks
- markov decision processes
- reasoning systems
- function approximation
- automated reasoning
- action selection
- control strategies
- knowledge base
- function approximators
- control policy
- control policies
- artificial intelligence
- robotic control
- reinforcement learning algorithms
- model free
- massively parallel
- fixed point
- optimal policy
- state space
- learning process
- multi agent