Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
reinforcement learning algorithm
|
| gptkbp:abbreviation |
gptkb:TD3
|
| gptkbp:address |
overestimation bias in actor-critic methods
|
| gptkbp:application |
robotics
continuous control simulated environments |
| gptkbp:basedOn |
gptkb:Deep_Deterministic_Policy_Gradient
|
| gptkbp:citation |
Addressing Function Approximation Error in Actor-Critic Methods
|
| gptkbp:citesPaper |
Lillicrap et al., 2015
|
| gptkbp:developedBy |
gptkb:David_Meger
gptkb:Herke_van_Hoof gptkb:Scott_Fujimoto |
| https://www.w3.org/2000/01/rdf-schema#label |
Twin Delayed DDPG
|
| gptkbp:improves |
gptkb:DDPG
other actor-critic algorithms |
| gptkbp:openSource |
gptkb:GitHub
|
| gptkbp:publicationYear |
2018
|
| gptkbp:publishedIn |
gptkb:arXiv
|
| gptkbp:technique |
delayed policy updates
target policy smoothing clipped double Q-learning |
| gptkbp:bfsParent |
gptkb:DDPG
|
| gptkbp:bfsLayer |
7
|