Josh Tobin

E515887

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 Statements Referenced by

All labels observed (1)

Label Occurrences
Josh Tobin canonical 1

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

Referenced by (1)

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