Search Results for author:
Found 26 papers, 7 papers with code
Inverse Risk-Sensitive Reinforcement Learning
We address the problem of inverse reinforcement learning in Markov decision processes where the agent is risk-sensitive.
Multi-Armed Bandits for Correlated Markovian Environments with Smoothed Reward Feedback
We analyze these algorithms under two types of smoothed reward feedback at the end of each epoch: a reward that is the discount-average of the discounted rewards within an epoch, and a reward that is the time-average of the rewards within an epoch.
On Gradient-Based Learning in Continuous Games
We formulate a general framework for competitive gradient-based learning that encompasses a wide breadth of multi-agent learning algorithms, and analyze the limiting behavior of competitive gradient-based learning algorithms using dynamical systems theory.
Combinatorial Bandits for Incentivizing Agents with Dynamic Preferences
The design of personalized incentives or recommendations to improve user engagement is gaining prominence as digital platform providers continually emerge.
Competitive Statistical Estimation with Strategic Data Sources
Recent work has explored mechanisms to ensure that the data sources share high quality data with a single data aggregator, addressing the issue of moral hazard.
Convergence Analysis of Gradient-Based Learning with Non-Uniform Learning Rates in Non-Cooperative Multi-Agent Settings
Considering a class of gradient-based multi-agent learning algorithms in non-cooperative settings, we provide local convergence guarantees to a neighborhood of a stable local Nash equilibrium.
Convergence of Learning Dynamics in Stackelberg Games
Using this insight, we develop a gradient-based update for the leader while the follower employs a best response strategy for which each stable critical point is guaranteed to be a Stackelberg equilibrium in zero-sum games.
Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games
In such games the state and action spaces are continuous and global Nash equilibria can be found be solving coupled Ricatti equations.
Constrained Upper Confidence Reinforcement Learning
Constrained Markov Decision Processes are a class of stochastic decision problems in which the decision maker must select a policy that satisfies auxiliary cost constraints.
Safe Reinforcement Learning of Control-Affine Systems with Vertex Networks
This paper focuses on finding reinforcement learning policies for control systems with hard state and action constraints.
Function Design for Improved Competitive Ratio in Online Resource Allocation with Procurement Costs
We study the problem of online resource allocation, where multiple customers arrive sequentially and the seller must irrevocably allocate resources to each incoming customer while also facing a procurement cost for the total allocation.
Minimax Optimization with Smooth Algorithmic Adversaries
This paper considers minimax optimization $\min_x \max_y f(x, y)$ in the challenging setting where $f$ can be both nonconvex in $x$ and nonconcave in $y$.
Zeroth-Order Methods for Convex-Concave Minmax Problems: Applications to Decision-Dependent Risk Minimization
Min-max optimization is emerging as a key framework for analyzing problems of robustness to strategically and adversarially generated data.
Approximate Regions of Attraction in Learning with Decision-Dependent Distributions
As data-driven methods are deployed in real-world settings, the processes that generate the observed data will often react to the decisions of the learner.
Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms
The hierarchical interaction between the actor and critic in actor-critic based reinforcement learning algorithms naturally lends itself to a game-theoretic interpretation.
Multiplayer Performative Prediction: Learning in Decision-Dependent Games
We show that under mild assumptions, the performatively stable equilibria can be found efficiently by a variety of algorithms, including repeated retraining and the repeated (stochastic) gradient method.
Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environments
This paper studies the problem of expected loss minimization given a data distribution that is dependent on the decision-maker's action and evolves dynamically in time according to a geometric decay process.
General sum stochastic games with networked information flows
Inspired by applications such as supply chain management, epidemics, and social networks, we formulate a stochastic game model that addresses three key features common across these domains: 1) network-structured player interactions, 2) pair-wise mixed cooperation and competition among players, and 3) limited global information toward individual decision-making.
Emergent segmentation from participation dynamics and multi-learner retraining
We study the participation and retraining dynamics that arise when both the learners and sub-populations of users are \emph{risk-reducing}, which cover a broad class of updates including gradient descent, multiplicative weights, etc.
Instance-dependent Sample Complexity Bounds for Zero-sum Matrix Games
We study the sample complexity of identifying an approximate equilibrium for two-player zero-sum $n\times 2$ matrix games.
Human adaptation to adaptive machines converges to game-theoretic equilibria
Our algorithms enable the machine to select the outcome of the co-adaptive interaction from a constellation of game-theoretic equilibria in action and policy spaces.
Stackelberg Games for Learning Emergent Behaviors During Competitive Autocurricula
Autocurricular training is an important sub-area of multi-agent reinforcement learning~(MARL) that allows multiple agents to learn emergent skills in an unsupervised co-evolving scheme.
Logarithmic Regret for Matrix Games against an Adversary with Noisy Bandit Feedback
If the row player uses the EXP3 strategy, an algorithm known for obtaining $\sqrt{T}$ regret against an arbitrary sequence of rewards, it is immediate that the row player also achieves $\sqrt{T}$ regret relative to the Nash equilibrium in this game setting.
Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits & Dueling Bandits
We design a near-optimal algorithm whose sample complexity matches the lower bound, up to log factors.
Initializing Services in Interactive ML Systems for Diverse Users
(ii) Suboptimal Local Solutions: The total loss (sum of loss functions across all users and all services) landscape is not convex even if the individual losses on a single service are convex, making it likely for the learning dynamics to get stuck in local minima.
Distribution-Free Guarantees for Systems with Decision-Dependent Noise
Our approach finds the open-loop control law that minimizes the worst-case loss, given that the noise induced by this control lies in its $(1 - p)$-confidence set for a predetermined $p$.
