Nir Levine
7 papers · 2017–2021 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(3)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(13)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
ICLR (3)
NIPS (3)
AAAI (1)
Top co-authors
Keywords
model compression
(1)
deep reinforcement learning
(1)
off-policy evaluation
(1)
online learning
(1)
maximum entropy
(1)
transfer learning
(1)
bayesian regularization
(1)
function approximation
(1)
knowledge distillation
(1)
value function approximation
(1)
batch reinforcement learning
(1)
stationary distribution
(1)
multi-armed bandit
(1)
regret bound
(1)
deep neural network
(1)
average reward mdp
(1)
least square
(1)
student network
(1)
deep q-network
(1)
teacher student learning
(1)
Papers
Balancing Constraints and Rewards with Meta-Gradient D4PG
ICLR 2021
A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs
NIPS 2020
Improved Knowledge Distillation via Teacher Assistant
AAAI 2020
Robust Reinforcement Learning for Continuous Control with Model Misspecification
ICLR 2020
Prediction, Consistency, Curvature: Representation Learning for Locally-Linear Control
ICLR 2020
Shallow Updates for Deep Reinforcement Learning
NIPS 2017
Rotting Bandits
NIPS 2017