Search Results for author:
Found 9 papers, 2 papers with code
A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent
In this paper, we propose Posterior Sampling Reinforcement Learning for Zero-sum Stochastic Games (PSRL-ZSG), the first online learning algorithm that achieves Bayesian regret bound of $O(HS\sqrt{AT})$ in the infinite-horizon zero-sum stochastic games with average-reward criterion.
Online Learning for Cooperative Multi-Player Multi-Armed Bandits
For the first setting, we propose a UCB-inspired algorithm that achieves $O(\log T)$ regret whether the rewards are IID or Markovian.
Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path
We introduce a generic template for developing regret minimization algorithms in the Stochastic Shortest Path (SSP) model, which achieves minimax optimal regret as long as certain properties are ensured.
Online Learning for Stochastic Shortest Path Model via Posterior Sampling
We consider the problem of online reinforcement learning for the Stochastic Shortest Path (SSP) problem modeled as an unknown MDP with an absorbing state.
Online Learning for Unknown Partially Observable MDPs
Learning optimal controllers for POMDPs when the model is unknown is harder.
Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation
We develop several new algorithms for learning Markov Decision Processes in an infinite-horizon average-reward setting with linear function approximation.
A Model-free Learning Algorithm for Infinite-horizon Average-reward MDPs with Near-optimal Regret
Recently, model-free reinforcement learning has attracted research attention due to its simplicity, memory and computation efficiency, and the flexibility to combine with function approximation.
Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes
Model-free reinforcement learning is known to be memory and computation efficient and more amendable to large scale problems.
PPD: Permutation Phase Defense Against Adversarial Examples in Deep Learning
In this paper, Permutation Phase Defense (PPD), is proposed as a novel method to resist adversarial attacks.
