Josh Tobin

E515887
machine learning researcher person reinforcement learning technique

Josh Tobin is a machine learning researcher known for his work on deep reinforcement learning, including co-developing the Hindsight Experience Replay technique.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

All labels observed (1)

Label Occurrences
Josh Tobin canonical 1

How this entity was disambiguated

Statements (22)

Predicate Object
instanceOf machine learning researcher ⓘ
person ⓘ
reinforcement learning technique ⓘ
aimsTo improve sample efficiency in reinforcement learning ⓘ
appliesTo goal-conditioned reinforcement learning ⓘ
basedOn relabeling failed trajectories with alternative goals ⓘ
coDeveloperOf Hindsight Experience Replay NERFINISHED ⓘ
fieldOfWork deep learning ⓘ
deep reinforcement learning ⓘ
machine learning ⓘ
reinforcement learning ⓘ
hasAuthor Josh Tobin NERFINISHED ⓘ
hasGivenTalkOn deep reinforcement learning for robotics ⓘ
knownFor Hindsight Experience Replay NERFINISHED ⓘ
notableWork Hindsight Experience Replay NERFINISHED ⓘ
proposedIn 2017 ⓘ
usedFor goal-based RL tasks ⓘ
robotic manipulation tasks ⓘ
sparse reward environments ⓘ
workFocus generalization in reinforcement learning ⓘ
robotics and control with deep RL ⓘ
sample-efficient reinforcement learning ⓘ

How these facts were elicited

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.

Hindsight Experience Replay → proposedBy → Josh Tobin ⓘ