Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics.

Runzhe Wu Ayush Sekhari Akshay Krishnamurthy Wen Sun

Published in: CoRR (2024)

Keyphrases

computationally efficient
reinforcement learning
dynamic model
linear program
piecewise linear
multi agent
highly nonlinear
data sets
neural network
lower bound
optimal policy
markov decision processes
black box
state action
temporal difference learning