Login / Signup
CIExplore: Curiosity and Influence-based Exploration in Multi-Agent Cooperative Scenarios with Sparse Rewards.
Huanhuan Yang
Dianxi Shi
Chenran Zhao
Guojun Xie
Shaowu Yang
Published in:
CIKM (2021)
Keyphrases
</>
reinforcement learning
sparse data
high dimensional
neural network
real world
markov decision processes
bandit problems
real time
website
linear combination
search strategies
learning scenarios
exploration strategy
multiarmed bandit