hanabi
Country:
- Europe > United Kingdom > England > Oxfordshire > Oxford (0.04)
- North America > United States > Pennsylvania > Allegheny County > Pittsburgh (0.04)
- North America > United States > Oregon (0.04)
- North America > United States > California > Santa Clara County > Palo Alto (0.04)
Technology:
Country:
- North America > United States > New York > New York County > New York City (0.14)
- North America > United States > New York > Richmond County > New York City (0.04)
- North America > United States > New York > Queens County > New York City (0.04)
- (5 more...)
Genre:
- Instructional Material (0.46)
- Research Report (0.46)
Technology:
Genre:
- Research Report > New Finding (1.00)
- Questionnaire & Opinion Survey (0.69)
- Research Report > Experimental Study > Negative Result (0.46)
Industry:
- Leisure & Entertainment > Games > Computer Games (1.00)
- Government > Regional Government > North America Government > United States Government (1.00)
- Government > Military (1.00)
Technology:
Off-TeamLearning
Second, OBL policies may bebrittle when paired with anoveltest time partner,e.g.
Country:
- North America > United States > Pennsylvania > Allegheny County > Pittsburgh (0.04)
- North America > United States > New York > New York County > New York City (0.04)
- North America > United States > California > Santa Clara County > Palo Alto (0.04)
- (2 more...)
Technology:
Country:
- North America > United States > Louisiana > Orleans Parish > New Orleans (0.04)
- North America > United States > California > San Diego County > San Diego (0.04)
- North America > United States > Arizona > Maricopa County > Phoenix (0.04)
- (5 more...)
Technology:
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning > Agents (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Reinforcement Learning (0.94)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Undirected Networks > Markov Models (0.68)
Off-Team Learning
Zero-shot coordination (ZSC) evaluates an algorithm by the performance of a team of agents that were trained independently under that algorithm. Off-belief learning (OBL) is a recent method that achieves state-of-the-art results in ZSC in the game Hanabi. However, the implementation of OBL relies on a belief model that experiences covariate shift. Moreover, during ad-hoc coordination, OBL or any other neural policy may experience test-time covariate shift.