James MacGlashan
7 papers · 2015–2022 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (17) π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (5)
π
Academic Marathon
(7)
π
Cross-Pollinator
(12)
π
Renaissance Researcher
(6)
π
Trend Setter
Conferences
IJCAI (2)
NIPS (2)
AAAI (1)
ICML (1)
RSS (1)
Top co-authors
Keywords
reinforcement learning
(3)
imitation learning
(2)
policy learning
(2)
reward function
(2)
inverse reinforcement learning
(1)
language grounding
(1)
robot learning
(1)
bayesian model
(1)
value estimation
(1)
temporal abstraction
(1)
natural language
(1)
robot manipulation
(1)
human feedback
(1)
reward shaping
(1)
general value function
(1)
soft actor-critic
(1)
goal inference
(1)
reward signal
(1)
reward decomposition
(1)
value decomposition
(1)
Papers
Value Function Decomposition for Iterative Design of Reinforcement Learning Agents
NIPS 2022
Gamma-Nets: Generalizing Value Estimation over Timescale
AAAI 2020
Interactive Learning from Policy-Dependent Human Feedback
ICML 2017
Showing versus doing: Teaching by demonstration
NIPS 2016
Between Imitation and Intention Learning
IJCAI 2015
Portable Option Discovery for Automated Learning Transfer in Object-Oriented Markov Decision Processes
IJCAI 2015
Grounding English Commands to Reward Functions
RSS 2015