OpenAI's Gym library contains a large, diverse set of environments that are useful benchmarks in reinforcement learning, under a single elegant Python API (with tools to develop new compliant environments) . The introduction of this library has proven a watershed moment for the reinforcement learning community, because it created an accessible set of benchmark environments that everyone could use (including wrapper important existing libraries), and because a standardized API let RL learning methods and environments from anywhere be trivially exchanged. This paper similarly introduces PettingZoo, a library of diverse set of multi-agent environments under a single elegant Python API, with tools to easily make new compliant environments.
Many problems in Machine Learning can be modeled as submodular optimization problems. Recent work has focused on stochastic or adaptive versions of these problems. We consider the Scenario Submodular Cover problem, which is a counterpart to the Stochastic Submodular Cover problem studied by Golovin and Krause (2011). In Scenario Submodular Cover, the goal is to produce a cover with minimum expected cost, where the expectation is with respect to an empirical joint distribution, given as input by a weighted sample of realizations. In contrast, in Stochastic Submodular Cover, the variables of the input distribution are assumed to be independent, and the distribution of each variable is given as input. Building on algorithms developed by Cicalese et al. (2014) and Golovin and Krause (2011) for related problems, we give two approximation algorithms for Scenario Submodular Cover over discrete distributions. The first achieves an approximation factor of O(log Qm), where m is the size of the sample and Q is the goal utility. The second, simpler algorithm achieves an approximation bound of O(log QW ), where Q is the goal utility and W is the sum of the integer weights. (Both bounds assume an integer-valued utility function.) Our results yield approximation bounds for other problems involving non-independent distributions that are explicitly specified by their support.
Nonstationarity" is a fundamental problem in cooperative multi-agent reinforcement learning (MARL)-each agent must relearn information about the other agent's policies due to the other agents learning, causing information to "ring" between agents and convergence to be slow. The MAILP model, introduced by Terry and Grammel (2020), is a novel model of information transfer during multi-agent learning. We use the MAILP model to show that increasing training centralization arbitrarily mitigates the slowing of convergence due to nonstationarity. The most centralized case of learning is parameter sharing, an uncommonly used MARL method, specific to environments with homogeneous agents, that bootstraps a single-agent reinforcement learning (RL) method and learns an identical policy for each agent. We experimentally replicate the result of increased learning centralization leading to better performance on the MARL benchmark set from Gupta et al. (2017). We further apply parameter sharing to 8 "more modern" single-agent deep RL (DRL) methods for the first time in the literature. With this, we achieved the best documented performance on a set of MARL benchmarks and achieved up to 38 times more average reward in as little as 7% as many episodes compared to documented parameter sharing arrangement. We finally offer a formal proof of a set of methods that allow parameter sharing to serve in environments with heterogeneous agents.Preprint. Under review.
A continuous-time quantum walk on a graph is a matrix-valued function exp(−iAt) over the reals, where A is the adjacency matrix of the graph. Such a quantum walk has universal perfect state transfer if for all vertices u, v, there is a time where the (v, u) entry of the matrix exponential has unit magnitude. We prove new characterizations of graphs with universal perfect state transfer. This extends results of Cameron et al. (Linear Algebra and Its Applications, 455:115-142, 2014). Also, we construct non-circulant families of graphs with universal perfect state transfer. All prior known constructions were circulants. Moreover, we prove that if a circulant, whose order is prime, prime squared, or a power of two, has universal perfect state transfer then its underlying graph must be complete. This is nearly tight since there are universal perfect state transfer circulants with non-prime-power order where some edges are missing.
Partially Observable Stochastic Games (POSGs), are the most general model of games used in Multi-Agent Reinforcement Learning (MARL), modeling actions and observations as happening sequentially for all agents. We introduce Agent Environment Cycle Games (AEC Games), a model of games based on sequential agent actions and observations. AEC Games can be thought of as sequential versions of POSGs, and we prove that they are equally powerful. We argue conceptually and through case studies that the AEC games model is useful in important scenarios in MARL for which the POSG model is not well suited. We additionally introduce "cyclically expansive curriculum learning," a new MARL curriculum learning method motivated by the AEC games model. It can be applied "for free, " and experimentally we show this technique to achieve up to 35.1% more total reward on average.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.