Engineering & Materials Science
Reinforcement learning
100%
Markov processes
57%
Learning algorithms
23%
Uncertainty
22%
Decoding
18%
Planning
12%
Sampling
11%
Decision making
10%
Resource allocation
10%
Throughput
10%
Costs
10%
Dynamic programming
8%
Data storage equipment
8%
Ultrashort pulses
8%
Feedback
8%
Deep neural networks
8%
Machine learning
8%
Supervised learning
8%
Set theory
7%
Experiments
7%
Entropy
7%
Linear programming
7%
Statistics
6%
Monitoring
6%
Crowdsourcing
6%
Deep learning
6%
Laser pulses
6%
Classifiers
6%
NP-hard
5%
Convex optimization
5%
Dynamical systems
5%
Time series
5%
Polynomials
5%
Mathematics
Reinforcement Learning
49%
Reward
39%
Regret
27%
Policy
24%
Markov Decision Process
23%
Multi-armed Bandit
20%
Online Learning
17%
Learning
17%
Bandit Problems
12%
Game
11%
Learning Algorithm
11%
Strategy
10%
Monitoring
9%
Performance
8%
Decoding
6%
Framework
6%
Q-learning
6%
Uncertainty
6%
Repeated Games
6%
Low-density Parity-check (LDPC) Codes
5%
Unknown
5%
Market
5%
Maximise
5%
Model
5%
Robust Optimization
5%
