Search Results for author:
Found 6 papers, 3 papers with code
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form
Building on the epigraph form, we propose a bisection search algorithm with a policy gradient subroutine and prove that it identifies an $\varepsilon$-optimal policy in an RCMDP with $\widetilde{\mathcal{O}}(\varepsilon^{-4})$ robust policy evaluations.
A unified view of likelihood ratio and reparameterization gradients
Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used to estimate gradients of expectations throughout machine learning and reinforcement learning; however, they are usually explained as simple mathematical tricks, with no insight into their nature.
A unified view of likelihood ratio and reparameterization gradients and an optimal importance sampling scheme
Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used throughout machine and reinforcement learning; however, they are usually explained as simple mathematical tricks without providing any insight into their nature.
Neural Replicator Dynamics
Policy gradient and actor-critic algorithms form the basis of many commonly used training techniques in deep reinforcement learning.
Total stochastic gradient algorithms and applications in reinforcement learning
Backpropagation and the chain rule of derivatives have been prominent; however, the total derivative rule has not enjoyed the same amount of attention.
PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos
Previously, the exploding gradient problem has been explained to be central in deep learning and model-based reinforcement learning, because it causes numerical issues and instability in optimization.
Model-based Reinforcement Learning
reinforcement-learning
+2
