Learning to Perform Physics Experiments via Deep Reinforcement Learning.
Misha DenilPulkit AgrawalTejas D. KulkarniTom ErezPeter W. BattagliaNando de FreitasPublished in: ICLR (Poster) (2017)
Keyphrases
- reinforcement learning
- learning systems
- learning algorithm
- learning problems
- learning process
- artificial intelligence
- learned knowledge
- function approximation
- supervised learning
- state space
- action selection
- partially observable
- active learning
- autonomous learning
- eligibility traces
- online learning
- dynamic programming
- learning community
- deep learning
- function approximators
- policy search