Shixiang Gu
12 papers · 2016–2023 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Conference Polyglot (5) π§ Keyword Pioneer π£ Hot Topic Early Bird π Interdisciplinary Bridge π Academic Marathon (7)
π
Academic Marathon
(7)
π
Cross-Pollinator
(9)
π
Renaissance Researcher
(5)
π±
Topic Pioneer
π
Trend Setter
π
Century Club
(12)
π
Conference Pioneer
π₯
Unstoppable
(6)
Conferences
ICLR (5)
ICML (3)
EMNLP (2)
CORL (1)
RSS (1)
Top co-authors
Keywords
off-policy learning
(2)
deep reinforcement learning
(2)
reinforcement learning
(2)
imitation learning
(1)
model predictive control
(1)
divergence minimization
(1)
offline reinforcement learning
(1)
policy gradient
(1)
conversational ai
(1)
policy learning
(1)
variance reduction
(1)
inverse reinforcement learning
(1)
value function
(1)
continuous control
(1)
model-based reinforcement learning
(1)
policy optimization
(1)
skill discovery
(1)
quadruped locomotion
(1)
reward function
(1)
sample efficiency
(1)
Papers
Large Language Models Can Self-Improve
EMNLP 2023
Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization
ICLR 2021
Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning
RSS 2020
Human-centric dialog training via offline reinforcement learning
EMNLP 2020
Dynamics-Aware Unsupervised Discovery of Skills
ICLR 2020
Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives
ICLR 2019
A Divergence Minimization Perspective on Imitation Learning Methods
CORL 2019
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning
ICLR 2019
Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning
ICLR 2018
The Mirage of Action-Dependent Baselines in Reinforcement Learning
ICML 2018
Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control
ICML 2017
Continuous Deep Q-Learning with Model-based Acceleration
ICML 2016