Sanjit Seshia
5 papers · 2017–2021 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (14) π Cross-Pollinator (8) π Interdisciplinary Bridge π Conference Polyglot (3) π§ Keyword Pioneer
π£
Hot Topic Early Bird
π₯
Unstoppable
(5)
Conferences
NIPS (2)
RSS (2)
ICLR (1)
Top co-authors
Keywords
reward learning
(2)
reinforcement learning
(1)
imitation learning
(1)
maximum entropy
(1)
preference learning
(1)
inverse reinforcement learning
(1)
label ranking
(1)
learning from demonstration
(1)
stochastic game
(1)
multi-agent coordination
(1)
controller synthesis
(1)
reward inference
(1)
human-agent interaction
(1)
adversarial game
(1)
control synthesis
(1)
task specification
(1)
population-based training
(1)
reactive control
(1)
human-ai coordination
(1)
multi-agent system
(1)
Papers
Entropy-Guided Control Improvisation
RSS 2021
Learning Heuristics for Quantified Boolean Formulas through Reinforcement Learning
ICLR 2020
On the Utility of Learning about Humans for Human-AI Coordination
NIPS 2019
Learning Task Specifications from Demonstrations
NIPS 2018
Active Preference-Based Learning of Reward Functions
RSS 2017