Login / Signup
DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization.
Aviral Kumar
Rishabh Agarwal
Tengyu Ma
Aaron C. Courville
George Tucker
Sergey Levine
Published in:
CoRR (2021)
Keyphrases
</>
reinforcement learning
state space
reinforcement learning algorithms
neural network
function approximation
model free
robotic control
learning algorithm
supervised learning
temporal difference
semi supervised
smoothing parameter