Search Results for author:
Found 23 papers, 3 papers with code
Dynamic Pricing and Learning with Long-term Reference Effects
We study a simple and novel reference price mechanism where reference price is the average of the past prices offered by the seller.
Dynamic Pricing and Learning with Bayesian Persuasion
Our main result is a computationally efficient online algorithm that achieves an $O(T^{2/3}(m\log T)^{1/3})$ regret bound when the valuation function is linear in the product quality.
Online Allocation and Learning in the Presence of Strategic Agents
We study the problem of allocating $T$ sequentially arriving items among $n$ homogeneous agents under the constraint that each agent must receive a pre-specified fraction of all items, with the objective of maximizing the agents' total valuation of items allocated to them.
Scale Free Adversarial Multi Armed Bandits
This technique plays a crucial role in our analysis for controlling the regret when using importance weighted estimators of unbounded losses.
Dynamic Pricing and Learning under the Bass Model
Equivalently, the goal is to minimize the regret which measures the revenue loss of the algorithm relative to the optimal expected revenue achievable under the stochastic Bass model with market size $m$ and time horizon $T$.
Reinforcement Learning for Integer Programming: Learning to Cut
In particular, we investigate a specific methodology for solving IPs, known as the Cutting Plane Method.
Learning in structured MDPs with convex cost functions: Improved regret bounds for inventory management
We consider the relatively less studied problem of designing a learning algorithm for this problem when the underlying demand distribution is unknown.
Discretizing Continuous Action Space for On-Policy Optimization
In this work, we show that discretizing action space for continuous control is a simple yet powerful technique for on-policy optimization.
Boosting Trust Region Policy Optimization by Normalizing Flows Policy
We propose to improve trust region policy search with normalizing flows policy.
Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy
Inspired by many applications of bipartite matching in online advertising and machine learning, we study a simple and natural iterative proportional allocation algorithm: Maintain a priority score $\priority_a$ for each node $a\in \mathds{A}$ on one side of the bipartition, initialized as $\priority_a=1$.
Implicit Policy for Reinforcement Learning
We introduce Implicit Policy, a general class of expressive policies that can flexibly represent complex action distributions in reinforcement learning, with efficient algorithms to compute entropy regularized policy gradients.
Exploration by Distributional Reinforcement Learning
We propose a framework based on distributional reinforcement learning and recent attempts to combine Bayesian parameter updates with deep reinforcement learning.
Distributional Reinforcement Learning
Efficient Exploration
+2
Optimistic posterior sampling for reinforcement learning: worst-case regret bounds
Our main result is a high probability regret upper bound of $\tilde{O}(D\sqrt{SAT})$ for any communicating MDP with $S$ states, $A$ actions and diameter $D$, when $T\ge S^5A$.
Bandits with Delayed, Aggregated Anonymous Feedback
In this problem, when the player pulls an arm, a reward is generated, however it is not immediately observed.
MNL-Bandit: A Dynamic Learning Approach to Assortment Selection
The retailer observes this choice and the objective is to dynamically learn the model parameters, while optimizing cumulative revenues over a selling horizon of length $T$.
Thompson Sampling for the MNL-Bandit
We consider a sequential subset selection problem under parameter uncertainty, where at each time step, the decision maker selects a subset of cardinality $K$ from $N$ possible items (arms), and observes a (bandit) feedback in the form of the index of one of the items in said subset, or none.
Posterior sampling for reinforcement learning: worst-case regret bounds
We present an algorithm based on posterior sampling (aka Thompson sampling) that achieves near-optimal worst-case regret bounds when the underlying Markov Decision Process (MDP) is communicating with a finite, though unknown, diameter.
Linear Contextual Bandits with Knapsacks
We consider the linear contextual bandit problem with resource consumption, in addition to reward generation.
An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectives
This problem was introduced by Badanidiyuru et al. (2014), who gave a computationally inefficient algorithm with near-optimal regret bounds for it.
Fast Algorithms for Online Stochastic Convex Programming
We introduce the online stochastic Convex Programming (CP) problem, a very general version of stochastic online problems which allows arbitrary concave objectives and convex feasibility constraints.
Bandits with concave rewards and convex knapsacks
In this paper, we consider a very general model for exploration-exploitation tradeoff which allows arbitrary concave rewards and convex constraints on the decisions across time, in addition to the customary limitation on the time horizon.
Thompson Sampling for Contextual Bandits with Linear Payoffs
Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems.
A Dynamic Near-Optimal Algorithm for Online Linear Programming
A natural optimization model that formulates many online resource allocation and revenue management problems is the online linear program (LP) in which the constraint matrix is revealed column by column along with the corresponding objective coefficient.
