|
gptkbp:instance_of
|
gptkb:Artificial_Intelligence
|
|
gptkbp:bfsLayer
|
3
|
|
gptkbp:bfsParent
|
gptkb:philosopher
|
|
gptkbp:adapted_into
|
new environments
|
|
gptkbp:applies_to
|
planning
reinforcement learning
model-based learning
|
|
gptkbp:based_on
|
gptkb:Monte_Carlo_Tree_Search
|
|
gptkbp:can_be
|
without a model of the environment
|
|
gptkbp:can_be_used_with
|
planning and learning
|
|
gptkbp:competitors
|
AI competitions
|
|
gptkbp:contributed_to
|
gptkb:Research_Institute
|
|
gptkbp:developed_by
|
gptkb:philosopher
|
|
gptkbp:enhances
|
sample efficiency
|
|
gptkbp:has_achievements
|
state-of-the-art performance
|
|
gptkbp:has_programs
|
gptkb:robot
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Mu Zero
|
|
gptkbp:improves
|
gptkb:Alpha_Zero
|
|
gptkbp:innovation
|
gptkb:Artificial_Intelligence
|
|
gptkbp:introduced
|
gptkb:2020
|
|
gptkbp:is
|
a generalization of Alpha Zero
|
|
gptkbp:is_a_framework_for
|
developing intelligent agents
|
|
gptkbp:is_a_tool_for
|
AI researchers
|
|
gptkbp:is_capable_of
|
long-term planning
multi-agent scenarios
learning from raw pixels
|
|
gptkbp:is_designed_for
|
games
|
|
gptkbp:is_designed_to
|
handle uncertainty
|
|
gptkbp:is_effective_against
|
complex environments
|
|
gptkbp:is_evaluated_by
|
benchmark tests
|
|
gptkbp:is_influenced_by
|
previous AI models
|
|
gptkbp:is_known_for
|
its efficiency
|
|
gptkbp:is_optimized_for
|
various applications
decision-making processes
|
|
gptkbp:is_part_of
|
the future of AI development
Deep Mind's research portfolio
Deep Reinforcement Learning algorithms
the evolution of AI algorithms
|
|
gptkbp:is_recognized_for
|
its innovative approach
|
|
gptkbp:is_related_to
|
self-play
|
|
gptkbp:is_tested_for
|
board games
Atari games
|
|
gptkbp:is_used_in
|
gptkb:video_game
|
|
gptkbp:key_issues
|
gptkb:software_framework
|
|
gptkbp:learns_move
|
gptkb:video_game
|
|
gptkbp:notable_inductees
|
real-world applications
|
|
gptkbp:notable_recipients
|
the field of AI.
|
|
gptkbp:publishes
|
gptkb:academic_journal
|
|
gptkbp:related_model
|
in certain contexts
learns from experience
|
|
gptkbp:resulted_in
|
years of research
|
|
gptkbp:specialization
|
different types of games
|
|
gptkbp:subject
|
ongoing research
|
|
gptkbp:successor
|
gptkb:Alpha_Go
|
|
gptkbp:technology
|
AI planning
|
|
gptkbp:training
|
gptkb:metropolitan_area
|
|
gptkbp:uses
|
reinforcement learning techniques
|
|
gptkbp:utilizes
|
gptkb:microprocessor
|