Login / Signup
Hindsight Goal Ranking on Replay Buffer for Sparse Reward Environment.
Tung Minh Luu
Chang D. Yoo
Published in:
CoRR (2021)
Keyphrases
</>
web search
mobile robot
dynamic environments
initially unknown
navigation tasks
sparse data
pairwise
high dimensional
virtual world
sparse representation
computing environments
agent learns
real time
long run
sparse coding
ranking algorithm
data sets