|
gptkbp:instance_of
|
gptkb:Artificial_Intelligence
|
|
gptkbp:applies_to
|
gptkb:Atari_Games
reinforcement learning
|
|
gptkbp:developed_by
|
gptkb:Volodymyr_Mnih
|
|
gptkbp:has_achieved
|
Atari game performance
|
|
gptkbp:has_applications_in
|
gptkb:robotics
healthcare
finance
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
DQN
|
|
gptkbp:improves
|
Q-learning
|
|
gptkbp:inspired_by
|
Q-learning
|
|
gptkbp:is_analyzed_in
|
gptkb:vehicles
AI safety
multi-agent systems
|
|
gptkbp:is_applied_in
|
gptkb:Atari_Games
|
|
gptkbp:is_based_on
|
gptkb:neural_networks
|
|
gptkbp:is_compared_to
|
gptkb:A3_C
gptkb:DDPG
TRPO
|
|
gptkbp:is_enhanced_by
|
gptkb:Double_DQN
gptkb:Dueling_DQN
Prioritized Experience Replay
|
|
gptkbp:is_evaluated_by
|
performance metrics
Atari 2600 games
human benchmarks
|
|
gptkbp:is_implemented_in
|
gptkb:Python
|
|
gptkbp:is_influenced_by
|
biological neural networks
human learning
|
|
gptkbp:is_noted_for
|
convergence speed
modularity
scalability
real-time decision making
adaptability
stability issues
sample efficiency
exploration strategies
robustness to noise
generalization capabilities
flexibility in architecture
transfer learning potential
|
|
gptkbp:is_part_of
|
gptkb:Tensor_Flow
gptkb:Deep_Reinforcement_Learning
gptkb:gymnasium
gptkb:Py_Torch
|
|
gptkbp:is_related_to
|
policy gradient methods
|
|
gptkbp:is_trained_in
|
large datasets
|
|
gptkbp:is_used_for
|
decision making
game playing
control tasks
|
|
gptkbp:is_used_in
|
video game AI
|
|
gptkbp:published_in
|
gptkb:Nature
|
|
gptkbp:requires
|
high computational power
|
|
gptkbp:uses
|
deep learning
|
|
gptkbp:utilizes
|
experience replay
target network
|
|
gptkbp:year_created
|
gptkb:2013
|
|
gptkbp:bfsParent
|
gptkb:Stable_Baselines
gptkb:Deep_Mind
gptkb:Keras-RL
gptkb:Lunar_Lander-v2
gptkb:Open_AI_Baselines
|
|
gptkbp:bfsLayer
|
5
|