Login / Signup
Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches.
Wen Sun
Nan Jiang
Akshay Krishnamurthy
Alekh Agarwal
John Langford
Published in:
COLT (2019)
Keyphrases
</>
model free
decision processes
reinforcement learning
reinforcement learning algorithms
function approximation
rl algorithms
policy iteration
markov decision processes
temporal difference
upper bound
state space
optimal policy
search space
decision problems
policy evaluation
vc dimension
special case
lower bound