|
gptkbp:instance_of
|
gptkb:Artificial_Intelligence
gptkb:software
|
|
gptkbp:bfsLayer
|
3
|
|
gptkbp:bfsParent
|
gptkb:philosopher
|
|
gptkbp:architectural_style
|
gptkb:microprocessor
|
|
gptkbp:coat_of_arms
|
gptkb:television_series
|
|
gptkbp:contributed_to
|
machine learning advancements
|
|
gptkbp:data_privacy
|
gptkb:theorem
|
|
gptkbp:developed_by
|
gptkb:philosopher
|
|
gptkbp:difficulty
|
high
|
|
gptkbp:exhibited_at
|
generalization ability
|
|
gptkbp:feedback
|
highly positive
|
|
gptkbp:field_of_study
|
gptkb:Artificial_Intelligence
|
|
gptkbp:finale_date
|
won
|
|
gptkbp:future_plans
|
AI applications in various fields
|
|
gptkbp:game_type
|
gptkb:Go
|
|
gptkbp:has_achievements
|
multiple tournament victories
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Alpha Go Zero
|
|
gptkbp:impact
|
gptkb:significant
revolutionized strategies
|
|
gptkbp:improves
|
continuous
|
|
gptkbp:influenced
|
AI game playing
|
|
gptkbp:input_output
|
board position
move probabilities
|
|
gptkbp:inspired
|
further AI developments
|
|
gptkbp:is_compared_to
|
gptkb:Alpha_Go_Master
|
|
gptkbp:is_evaluated_by
|
gptkb:Monte_Carlo_Tree_Search
win rate
self-play games
|
|
gptkbp:legacy
|
pioneering AI in games
|
|
gptkbp:network
|
used
|
|
gptkbp:notable_feature
|
no prior knowledge
learns without human data
|
|
gptkbp:notable_match
|
Alpha Go Lee
|
|
gptkbp:number_of_games
|
over 100,000
|
|
gptkbp:orbital_period
|
40 million
|
|
gptkbp:performance
|
exceeded human players
|
|
gptkbp:provides_information_on
|
generated by itself
|
|
gptkbp:publishes
|
multiple research papers
|
|
gptkbp:rank
|
superhuman
top Go player
|
|
gptkbp:release_date
|
October 2017
|
|
gptkbp:release_year
|
gptkb:2017
|
|
gptkbp:result
|
dominant performance
|
|
gptkbp:significance
|
gptkb:Research_Institute
No human data used for training
|
|
gptkbp:strategic_importance
|
high
|
|
gptkbp:style_of_play
|
gptkb:theorem
|
|
gptkbp:successor
|
gptkb:Alpha_Go
|
|
gptkbp:tactics
|
aggressive and innovative
|
|
gptkbp:training
|
gptkb:military_unit
gptkb:Alpha_Zero
several days
adaptive
distributed computing
reinforcement learning
iterative improvement
Self-Play
|
|
gptkbp:user_base
|
researchers and developers
|