Search Results for author:
Found 14 papers, 1 papers with code
O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models
Recent advancements in large language models (LLMs) have exhibited promising performance in solving sequential decision-making problems.
Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas
In social psychology, Social Value Orientation (SVO) describes an individual's propensity to allocate resources between themself and others.
Melting Pot 2.0
Melting Pot is a research tool developed to facilitate work on multi-agent artificial intelligence, and provides an evaluation protocol that measures generalization to novel social partners in a set of canonical test scenarios.
A Regret Minimization Approach to Multi-Agent Control
We study the problem of multi-agent control of a dynamical system with known dynamics and adversarial disturbances.
One More Step Towards Reality: Cooperative Bandits with Imperfect Communication
However, most research for this problem focuses exclusively on the setting with perfect communication, whereas in most real-world distributed settings, communication is often over stochastic networks, with arbitrary corruptions and delays.
Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication
Distributed exploration reduces sampling complexity in multi-agent RL (MARL).
When to Call Your Neighbor? Strategic Communication in Cooperative Stochastic Bandits
We propose \textit{ComEx}, a novel cost-effective communication protocol in which the group achieves the same order of performance as full communication while communicating only $O(\log T)$ number of messages.
Distributed Bandits: Probabilistic Communication on $d$-regular Graphs
Every edge in the graph has probabilistic weight $p$ to account for the ($1\!-\! p$) probability of a communication link failure.
On Using Hamiltonian Monte Carlo Sampling for Reinforcement Learning Problems in High-dimension
Value function based reinforcement learning (RL) algorithms, for example, $Q$-learning, learn optimal policies from datasets of actions, rewards, and state transitions.
It Doesn’t Get Better and Here’s Why: A Fundamental Drawback in Natural Extensions of UCB to Multi-agent Bandits
We identify a fundamental drawback of natural extensions of Upper Confidence Bound (UCB) algorithms to the multi-agent bandit problem in which multiple agents facing the same explore-exploit problem can share information.
Heterogeneous Explore-Exploit Strategies on Multi-Star Networks
To do so we study a class of distributed stochastic bandit problems in which agents communicate over a multi-star network and make sequential choices among options in the same uncertain environment.
Distributed Learning: Sequential Decision Making in Resource-Constrained Environments
We study cost-effective communication strategies that can be used to improve the performance of distributed learning systems in resource-constrained environments.
A Dynamic Observation Strategy for Multi-agent Multi-armed Bandit Problem
We define and analyze a multi-agent multi-armed bandit problem in which decision-making agents can observe the choices and rewards of their neighbors under a linear observation cost.
Heterogeneous Stochastic Interactions for Multiple Agents in a Multi-armed Bandit Problem
We define and analyze a multi-agent multi-armed bandit problem in which decision-making agents can observe the choices and rewards of their neighbors.
