Login / Signup
Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards.
Katherine Metcalf
Miguel Sarabia
Natalie Mackraz
Barry-John Theobald
Published in:
CoRR (2024)
Keyphrases
</>
reinforcement learning
markov decision processes
multi agent
real time
state space
function approximation
model free
dynamic model
computationally expensive
lightweight
user preferences
sample size
cost effective
decision trees
learning algorithm
machine learning
database