Statements (52)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
algorithm
|
| gptkbp:appliesTo |
reinforcement learning
|
| gptkbp:developedBy |
Schulman_et_al.
|
| gptkbp:enables |
learning from failures
|
| gptkbp:hasRelatedPatent |
healthcare
finance autonomous driving |
| https://www.w3.org/2000/01/rdf-schema#label |
Hindsight Experience Replay
|
| gptkbp:improves |
sample efficiency
|
| gptkbp:isAttendedBy |
research community
industry practitioners |
| gptkbp:isBasedOn |
off-policy learning
|
| gptkbp:isConsidered |
state-of-the-art
|
| gptkbp:isDocumentedIn |
conference proceedings
journals academic papers technical reports |
| gptkbp:isEvaluatedBy |
simulated environments
robotic tasks Atari_games |
| gptkbp:isExaminedBy |
tutorials
workshops online courses webinars seminars |
| gptkbp:isInfluencedBy |
Q-learning
experience replay techniques temporal difference learning |
| gptkbp:isLocatedIn |
gptkb:PyTorch
TensorFlow |
| gptkbp:isPartOf |
gptkb:DDPG
DQN deep reinforcement learning prioritized experience replay standard experience replay |
| gptkbp:isRelatedTo |
goal-conditioned reinforcement learning
|
| gptkbp:isSupportedBy |
theoretical analysis
empirical studies |
| gptkbp:isUsedBy |
improve exploration
optimize policies train agents |
| gptkbp:isUsedFor |
transfer learning
multi-task learning other_RL_algorithms |
| gptkbp:isUsedIn |
robotics
game playing |
| gptkbp:isUtilizedIn |
continuous action spaces
discrete action spaces |
| gptkbp:mayHave |
policy learning
|
| gptkbp:reduces |
training time
|
| gptkbp:uses |
experience replay
|
| gptkbp:wasAffecting |
2017
|