control problem
Tight Rates for Bandit Control Beyond Quadratics
In this paper, we provide an affirmative answer to this question.
Technology:
EffectsofSafetyStateAugmentationon SafeExploration
There are still, however, some unsolved challenges for a successful deployment of RL such as efficient learning of constrained or safe Markov Decision Processes (MDPs) [4].
Technology:
Country:
- North America > United States > Illinois (0.04)
- Asia > Middle East > Jordan (0.04)
- Oceania > Australia > New South Wales (0.04)
Technology:
Country:
- North America > United States > Illinois (0.04)
- Asia > Middle East > Jordan (0.04)
- Oceania > Australia > New South Wales (0.04)
Technology:
Country:
- North America > United States > Maryland (0.04)
- Asia > Middle East > Jordan (0.04)
Industry:
- Energy (1.00)
- Government > Regional Government > North America Government > United States Government (0.46)
Technology:
Country:
- North America > United States > Arizona (0.05)
- North America > United States > North Carolina (0.04)
- Europe > Germany > Berlin (0.04)
- Asia > Myanmar > Tanintharyi Region > Dawei (0.04)
Industry:
- Health & Medicine > Health Care Technology (0.93)
- Health & Medicine > Therapeutic Area > Neurology (0.68)
- Health & Medicine > Therapeutic Area > Orthopedics/Orthopedic Surgery (0.46)
Technology:
- Information Technology > Artificial Intelligence > Robots (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Agents (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)
Attacks on Online Learners: a Teacher-Student Analysis
Machine learning models are famously vulnerable to adversarial attacks: small ad-hoc perturbations of the data that can catastrophically alter the model predictions.
Industry:
- Education (0.93)
- Information Technology > Security & Privacy (0.89)
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (0.93)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Regression (0.68)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.67)
Country:
- Europe > Netherlands > South Holland > Delft (0.04)
- North America > United States > Massachusetts > Middlesex County > Belmont (0.04)
- North America > United States > New York > New York County > New York City (0.04)
- (2 more...)
Technology:
ContinuousDeepQ-LearninginOptimalControl Problems: NormalizedAdvantageFunctionsAnalysis
One of the most effectivecontinuous deep reinforcement learning algorithms is normalized advantage functions (NAF).
Country:
- Europe > Russia (0.14)
- Asia > Russia > Ural Federal District > Sverdlovsk Oblast > Yekaterinburg (0.05)
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (1.00)