Statements (27)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:Artificial_Intelligence
|
| gptkbp:applies_to |
continuous action spaces
|
| gptkbp:based_on |
actor-critic architecture
|
| gptkbp:can_be_combined_with |
other techniques
|
| gptkbp:developed_by |
gptkb:Google_Deep_Mind
|
| gptkbp:first_introduced |
gptkb:2015
|
| gptkbp:has_expansion |
deterministic policy gradient methods
|
| https://www.w3.org/2000/01/rdf-schema#label |
DDPG
|
| gptkbp:improves |
gptkb:DQN
|
| gptkbp:is_applied_in |
healthcare
finance autonomous driving |
| gptkbp:is_used_in |
gptkb:robotics
game playing control tasks |
| gptkbp:requires |
hyperparameter tuning
|
| gptkbp:sensitivity |
initialization
|
| gptkbp:suffered_from |
overestimation bias
|
| gptkbp:type |
gptkb:machine_learning
|
| gptkbp:uses |
deep neural networks
|
| gptkbp:utilizes |
experience replay
target networks |
| gptkbp:bfsParent |
gptkb:Stable_Baselines
gptkb:Keras-RL gptkb:Lunar_Lander-v2 gptkb:Open_AI_Baselines |
| gptkbp:bfsLayer |
5
|