Hubert Soyer
5 papers · 2015–2020 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (12) 🌍 Conference Polyglot (4)
🏃
Academic Marathon
(5)
🚀
Conference Pioneer
Conferences
ICLR (2)
AAAI (1)
ICML (1)
NAACL (1)
Top co-authors
Keywords
multi-task learning
(2)
reinforcement learning
(1)
policy gradient
(1)
policy learning
(1)
deep learning
(1)
value function estimation
(1)
value estimation
(1)
atari game
(1)
game ai
(1)
value-based method
(1)
distributed deep reinforcement learning
(1)
actor-learner architecture
(1)
off-policy correction
(1)
importance weighted
(1)
population-based training
(1)
reward normalization
(1)
value normalization
(1)
deep reinforcement learning
(1)
popart normalization
(1)
Papers
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
ICLR 2020
V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
ICLR 2020
Multi-Task Deep Reinforcement Learning with PopArt
AAAI 2019
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
ICML 2018
CroVeWA: Crosslingual Vector-Based Writing Assistance
NAACL 2015