Sign in
Abstract Demonstrations and Adaptive Exploration for Efficient and Stable Multi-step Sparse Reward Reinforcement Learning.
Xintong Yang
Ze Ji
Jing Wu
Yu-Kun Lai
Published in:
ICAC (2022)
Keyphrases
</>
multi step
reinforcement learning
single step
lower bounding
markov decision processes
function approximation
distance computation
tumor classification
high dimensional
learning process
exploration strategy
active exploration
eligibility traces
learning agent
convergence speed
optimal policy
pairwise