Search Results for author:
Found 29 papers, 9 papers with code
Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games
Our algorithm simultaneously achieves a Nash regret and a regret bound of $O(T^{4/5})$ for potential games, which matches the best available result, without using additional projection steps.
DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning
Communication lays the foundation for cooperation in human society and in multi-agent reinforcement learning (MARL).
Taming the Exponential Action Set: Sublinear Regret and Fast Convergence to Nash Equilibrium in Online Congestion Games
The congestion game is a powerful model that encompasses a range of engineering systems such as traffic networks and resource allocation.
Online Influence Maximization under Decreasing Cascade Model
The effect is neglected by previous OIM works under IC and linear threshold models.
Semantically Aligned Task Decomposition in Multi-Agent Reinforcement Learning
The difficulty of appropriately assigning credit is particularly heightened in cooperative MARL with sparse reward, due to the concurrent time and structural scales involved.
Information Design in Multi-Agent Reinforcement Learning
To thrive in those environments, the agent needs to influence other agents so their actions become more helpful and less harmful.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Diverse Policy Optimization for Structured Action Space
We propose a simple and effective RL method, Diverse Policy Optimization (DPO), to model the policies in structured action space as the energy-based models (EBM) by following the probabilistic RL framework.
Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization
Learning Markov decision processes (MDP) in an adversarial environment has been a challenging problem.
Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning
e. g., an agent is a random policy while other agents are medium policies.
Online Policy Optimization for Robust MDP
Reinforcement learning (RL) has exceeded human performance in many synthetic settings such as video games and Go.
Relative Policy-Transition Optimization for Fast Policy Transfer
Integrating the two algorithms results in the complete Relative Policy-Transition Optimization (RPTO) algorithm, in which the policy interacts with the two environments simultaneously, such that data collections from two environments, policy and transition updates are completed in one closed loop to form a principled learning framework for policy transfer.
Algorithms and Theory for Supervised Gradual Domain Adaptation
We thus study the problem of supervised gradual domain adaptation, where labeled data from shifting distributions are available to the learner along the trajectory, and we aim to learn a classifier on a target data distribution of interest.
Provably Efficient Convergence of Primal-Dual Actor-Critic with Nonlinear Function Approximation
We study the convergence of the actor-critic algorithm with nonlinear function approximation under a nonconvex-nonconcave primal-dual formulation.
Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization
Temporal difference (TD) learning is a widely used method to evaluate policies in reinforcement learning.
CGIBNet: Bandwidth-constrained Communication with Graph Information Bottleneck in Multi-Agent Reinforcement Learning
The node information compression aims to address the problem of what to communicate via learning compact node representations.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Edge Rewiring Goes Neural: Boosting Network Resilience without Rich Features
In this case, GNNs can barely learn useful information, resulting in prohibitive difficulty in making actions for successively rewiring edges under a reinforcement learning context.
Incentivizing an Unknown Crowd
Motivated by the common strategic activities in crowdsourcing labeling, we study the problem of sequential eliciting information without verification (EIWV) for workers with a heterogeneous and unknown crowd.
Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning
Specifically, Shapley Value and its desired properties are leveraged in deep MARL to credit any combinations of agents, which grants us the capability to estimate the individual credit for each agent.
Cascading Bandit under Differential Privacy
This paper studies \emph{differential privacy (DP)} and \emph{local differential privacy (LDP)} in cascading bandits.
Combinatorial Bandits under Strategic Manipulations
Strategic behavior against sequential learning methods, such as "click framing" in real recommendation systems, have been widely observed.
Learning and Testing Variable Partitions
In particular we show that $1.$ Given a function that has a $k$-partition of cost $\delta$, a partition of cost $\mathcal{O}(k n^2)(\delta + \epsilon)$ can be learned in time $\tilde{\mathcal{O}}(n^2 \mathrm{poly} (1/\epsilon))$ for any $\epsilon > 0$.
The Gambler's Problem and Beyond
We analyze the Gambler's problem, a simple reinforcement learning problem where the gambler has the chance to double or lose the bets until the target is reached.
Privacy-Preserving Q-Learning with Functional Noise in Continuous Spaces
Our aim is to protect the value function approximator, without regard to the number of states queried to the function.
Recurrent Existence Determination Through Policy Optimization
Binary determination of the presence of objects is one of the problems where humans perform extraordinarily better than computer vision systems, in terms of both speed and preciseness.
Privacy-preserving Q-Learning with Functional Noise in Continuous State Spaces
Our aim is to protect the value function approximator, without regard to the number of states queried to the function.
Beyond Winning and Losing: Modeling Human Motivations and Behaviors with Vector-valued Inverse Reinforcement Learning
In recent years, reinforcement learning methods have been applied to model gameplay with great success, achieving super-human performance in various environments, such as Atari, Go and Poker.
Beyond Winning and Losing: Modeling Human Motivations and Behaviors Using Inverse Reinforcement Learning
Using the results of motivation modeling, we also predict and explain their diverse gameplay behaviors and provide a quantitative assessment of how the redesign of the game environment impacts players' behaviors.
Metatrace Actor-Critic: Online Step-size Tuning by Meta-gradient Descent for Reinforcement Learning Control
Finally, we apply Metatrace for control with nonlinear function approximation in 5 games in the Arcade Learning Environment where we explore how it impacts learning speed and robustness to initial step-size choice.
Policy Optimization with Second-Order Advantage Information
Policy optimization on high-dimensional continuous control tasks exhibits its difficulty caused by the large variance of the policy gradient estimators.
