Proximal Policy Optimization Algorithms
GPTKB entity
Statements (27)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:algorithm
gptkb:reinforcement_learning_algorithm |
| gptkbp:abbreviation |
PPO
|
| gptkbp:advantage |
simplicity
robustness sample efficiency |
| gptkbp:appliesTo |
gptkb:game_AI
robotics autonomous control |
| gptkbp:category |
gptkb:artificial_intelligence
gptkb:machine_learning |
| gptkbp:developedBy |
gptkb:OpenAI
|
| gptkbp:hasComponent |
value function
policy gradient clipped surrogate objective |
| gptkbp:implementedIn |
gptkb:TensorFlow
gptkb:Stable_Baselines gptkb:PyTorch |
| gptkbp:introducedIn |
2017
|
| gptkbp:notablePublication |
Proximal Policy Optimization Algorithms (Schulman et al., 2017)
|
| gptkbp:relatedTo |
gptkb:Trust_Region_Policy_Optimization
Actor-Critic Methods |
| gptkbp:usedFor |
gptkb:reinforcement_learning
policy optimization |
| gptkbp:bfsParent |
gptkb:Proximal_Policy_Optimization_(PPO)
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
Proximal Policy Optimization Algorithms
|