Hengshuai Yao
11 papers · 2009–2023 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🗺️ Taxonomy Completionist (28) 🏃 Academic Marathon · Half 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Gold 🐣 Hot Topic Early Bird
🌱
Topic Pioneer
🌈
Renaissance Researcher
(5)
🔥
Unstoppable · Bronze
🚀
Conference Pioneer
💎
Century Club · Bronze
📈
Trend Setter
🗃️
Keyword Collector
(66)
Venues
Top co-authors
Research topics
Reinforcement Learning
(9)
Methods
(9)
Artificial Intelligence
(7)
Machine Learning
(7)
Core AI
(6)
Applications · Reinforcement Learning
(5)
Learning Types · Machine Learning
(5)
Deep Learning
(3)
Learning Types · Deep Learning
(3)
Optimization & Theory
(3)
Computer Vision
(1)
Data Science & Analytics
(1)
Knowledge & Reasoning
(1)
Analysis
(1)
Applications · Data Science & Analytics
(1)
Keywords
value function
(3)
reinforcement learning
(3)
function approximation
(3)
model-based reinforcement learning
(3)
temporal difference learning
(2)
quantile-based exploration
(2)
off-policy learning
(2)
distributional reinforcement learning
(2)
reward function
(1)
continuous control
(1)
weakly supervised learning
(1)
natural gradient
(1)
dyna architecture
(1)
policy gradient
(1)
linear function approximation
(1)
policy learning
(1)
stochastic approximation
(1)
multi-step planning
(1)
autonomous driving
(1)
policy evaluation
(1)
Papers
The Sufficiency of Off-Policyness and Soft Clipping: PPO Is Still Insufficient according to an Off-Policy Measure
AAAI 2023
Understanding and mitigating the limitations of prioritized experience replay
UAI 2022
Breaking the Deadly Triad with a Target Network
ICML 2021
Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation
ICML 2020
Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings
IJCAI 2020
ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search
AAAI 2019
Distributional Reinforcement Learning for Efficient Exploration
ICML 2019
Hill Climbing on Value Estimates for Search-control in Dyna
IJCAI 2019
QUOTA: The Quantile Option Architecture for Reinforcement Learning
AAAI 2019
Universal Option Models
NeurIPS 2014
Multi-Step Dyna Planning for Policy Evaluation and Control
NeurIPS 2009