PyTorchKR Papers

최신 논문

총 1,869편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2001.09318

Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors

How can societies learn to enforce and comply with social norms? Here we investigate the learning dynamics and emergence of compliance and enforcement of social norms in a foraging game, implemented in a multi-agent reinforcement learning setting. In this spatiotemporally extended game, individuals are incentivized to implement complex berry-foraging policies and punish transgressions against social taboos covering specific berry types. We show that agents benefit when eating poisonous berries is taboo, meaning the behavior is punished by other agents, as this helps overcome a credit-assignment problem in discovering delayed health effects. Critically, however, we also show that introducing an additional taboo, which results in punishment for eating a harmless berry, improves the rate and stability with which agents learn to punish taboo violations and comply with taboos. Counterintuitively, our results show that an arbitrary taboo (a "silly rule") can enhance social learning dynamics and achieve better outcomes in the middle stages of learning. We discuss the results in the context of studying normativity as a group-level emergent phenomenon.

arXiv:2001.07993

On Solving Cooperative MARL Problems with a Few Good Experiences

Cooperative Multi-agent Reinforcement Learning (MARL) is crucial for cooperative decentralized decision learning in many domains such as search and rescue, drone surveillance, package delivery and fire fighting problems. In these domains, a key challenge is learning with a few good experiences, i.e., positive reinforcements are obtained only in a few situations (e.g., on extinguishing a fire or tracking a crime or delivering a package) and in most other situations there is zero or negative reinforcement. Learning decisions with a few good experiences is extremely challenging in cooperative MARL problems due to three reasons. First, compared to the single agent case, exploration is harder as multiple agents have to be coordinated to receive a good experience. Second, environment is not stationary as all the agents are learning at the same time (and hence change policies). Third, scale of problem increases significantly with every additional agent. Relevant existing work is extensive and has focussed on dealing with a few good experiences in single-agent RL problems or on scalable approaches for handling non-stationarity in MARL problems. Unfortunately, neither of these approaches (or their extensions) are able to address the problem of sparse good experiences effectively. Therefore, we provide a novel fictitious self imitation approach that is able to simultaneously handle non-stationarity and sparse good experiences in a scalable manner. Finally, we provide a thorough comparison (experimental or descriptive) against relevant cooperative MARL algorithms to demonstrate the utility of our approach.

arXiv:2001.07527

Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping

We present a new model-based reinforcement learning algorithm, Cooperative Prioritized Sweeping, for efficient learning in multi-agent Markov decision processes. The algorithm allows for sample-efficient learning on large problems by exploiting a factorization to approximate the value function. Our approach only requires knowledge about the structure of the problem in the form of a dynamic decision network. Using this information, our method learns a model of the environment and performs temporal difference updates which affect multiple joint states and actions at once. Batch updates are additionally performed which efficiently back-propagate knowledge throughout the factored Q-function. Our method outperforms the state-of-the-art algorithm sparse cooperative Q-learning algorithm, both on the well-known SysAdmin benchmark and randomized environments.

arXiv:2001.06487

Algorithms in Multi-Agent Systems: A Holistic Perspective from Reinforcement Learning and Game Theory

Deep reinforcement learning (RL) has achieved outstanding results in recent years, which has led a dramatic increase in the number of methods and applications. Recent works are exploring learning beyond single-agent scenarios and considering multi-agent scenarios. However, they are faced with lots of challenges and are seeking for help from traditional game-theoretic algorithms, which, in turn, show bright application promise combined with modern algorithms and boosting computing power. In this survey, we first introduce basic concepts and algorithms in single agent RL and multi-agent systems; then, we summarize the related algorithms from three aspects. Solution concepts from game theory give inspiration to algorithms which try to evaluate the agents or find better solutions in multi-agent systems. Fictitious self-play becomes popular and has a great impact on the algorithm of multi-agent reinforcement learning. Counterfactual regret minimization is an important tool to solve games with incomplete information, and has shown great strength when combined with deep learning.

arXiv:2001.05458

Inducing Cooperative behaviour in Sequential-Social dilemmas through Multi-Agent Reinforcement Learning using Status-Quo Loss

In social dilemma situations, individual rationality leads to sub-optimal group outcomes. Several human engagements can be modeled as a sequential (multi-step) social dilemmas. However, in contrast to humans, Deep Reinforcement Learning agents trained to optimize individual rewards in sequential social dilemmas converge to selfish, mutually harmful behavior. We introduce a status-quo loss (SQLoss) that encourages an agent to stick to the status quo, rather than repeatedly changing its policy. We show how agents trained with SQLoss evolve cooperative behavior in several social dilemma matrix games. To work with social dilemma games that have visual input, we propose GameDistill. GameDistill uses self-supervision and clustering to automatically extract cooperative and selfish policies from a social dilemma game. We combine GameDistill and SQLoss to show how agents evolve socially desirable cooperative behavior in the Coin Game.

arXiv:2001.04527

Multi-Robot Formation Control Using Reinforcement Learning

In this paper, we present a machine learning approach to move a group of robots in a formation. We model the problem as a multi-agent reinforcement learning problem. Our aim is to design a control policy for maintaining a desired formation among a number of agents (robots) while moving towards a desired goal. This is achieved by training our agents to track two agents of the group and maintain the formation with respect to those agents. We consider all agents to be homogeneous and model them as unicycle [1]. In contrast to the leader-follower approach, where each agent has an independent goal, our approach aims to train the agents to be cooperative and work towards the common goal. Our motivation to use this method is to make a fully decentralized multi-agent formation system and scalable for a number of agents.

arXiv:2001.01096공식 코드 · Papers with Code

Represented Value Function Approach for Large Scale Multi Agent Reinforcement Learning

In this paper, we consider the problem of large scale multi agent reinforcement learning. Firstly, we studied the representation problem of the pairwise value function to reduce the complexity of the interactions among agents. Secondly, we adopt a l2-norm trick to ensure the trivial term of the approximated value function is bounded. Thirdly, experimental results on battle game demonstrate the effectiveness of the proposed approach.

arXiv:2001.00918

Fairness in Multi-agent Reinforcement Learning for Stock Trading

Unfair stock trading strategies have been shown to be one of the most negative perceptions that customers can have concerning trading and may result in long-term losses for a company. Investment banks usually place trading orders for multiple clients with the same target assets but different order sizes and diverse requirements such as time frame and risk aversion level, thereby total earning and individual earning cannot be optimized at the same time. Orders executed earlier would affect the market price level, so late execution usually means additional implementation cost. In this paper, we propose a novel scheme that utilizes multi-agent reinforcement learning systems to derive stock trading strategies for all clients which keep a balance between revenue and fairness. First, we demonstrate that Reinforcement learning (RL) is able to learn from experience and adapt the trading strategies to the complex market environment. Secondly, we show that the Multi-agent RL system allows developing trading strategies for all clients individually, thus optimizing individual revenue. Thirdly, we use the Generalized Gini Index (GGI) aggregation function to control the fairness level of the revenue across all clients. Lastly, we empirically demonstrate the superiority of the novel scheme in improving fairness meanwhile maintaining optimization of revenue.

arXiv:1912.12671

Individual specialization in multi-task environments with multiagent reinforcement learners

There is a growing interest in Multi-Agent Reinforcement Learning (MARL) as the first steps towards building general intelligent agents that learn to make low and high-level decisions in non-stationary complex environments in the presence of other agents. Previous results point us towards increased conditions for coordination, efficiency/fairness, and common-pool resource sharing. We further study coordination in multi-task environments where several rewarding tasks can be performed and thus agents don't necessarily need to perform well in all tasks, but under certain conditions may specialize. An observation derived from the study is that epsilon greedy exploration of value-based reinforcement learning methods is not adequate for multi-agent independent learners because the epsilon parameter that controls the probability of selecting a random action synchronizes the agents artificially and forces them to have deterministic policies at the same time. By using policy-based methods with independent entropy regularised exploration updates, we achieved a better and smoother convergence. Another result that needs to be further investigated is that with an increased number of agents specialization tends to be more probable.

arXiv:1912.06875

Natural Actor-Critic Converges Globally for Hierarchical Linear Quadratic Regulator

Multi-agent reinforcement learning has been successfully applied to a number of challenging problems. Despite these empirical successes, theoretical understanding of different algorithms is lacking, primarily due to the curse of dimensionality caused by the exponential growth of the state-action space with the number of agents. We study a fundamental problem of multi-agent linear quadratic regulator (LQR) in a setting where the agents are partially exchangeable. In this setting, we develop a hierarchical actor-critic algorithm, whose computational complexity is independent of the total number of agents, and prove its global linear convergence to the optimal policy. As LQRs are often used to approximate general dynamic systems, this paper provides an important step towards a better understanding of general hierarchical mean-field multi-agent reinforcement learning.

arXiv:1912.05676

Biases for Emergent Communication in Multi-agent Reinforcement Learning

We study the problem of emergent communication, in which language arises because speakers and listeners must communicate information in order to solve tasks. In temporally extended reinforcement learning domains, it has proved hard to learn such communication without centralized training of agents, due in part to a difficult joint exploration problem. We introduce inductive biases for positive signalling and positive listening, which ease this problem. In a simple one-step environment, we demonstrate how these biases ease the learning problem. We also apply our methods to a more extended environment, showing that agents with these inductive biases achieve better performance, and analyse the resulting communication protocols.

arXiv:1912.03851

Intelligent Coordination among Multiple Traffic Intersections Using Multi-Agent Reinforcement Learning

We use Asynchronous Advantage Actor Critic (A3C) for implementing an AI agent in the controllers that optimize flow of traffic across a single intersection and then extend it to multiple intersections by considering a multi-agent setting. We explore three different methodologies to address the multi-agent problem - (1) use of asynchronous property of A3C to control multiple intersections using a single agent (2) utilise self/competitive play among independent agents across multiple intersections and (3) ingest a global reward function among agents to introduce cooperative behavior between intersections. We observe that (1) & (2) leads to a reduction in traffic congestion. Additionally the use of (3) with (1) & (2) led to a further reduction in congestion.

arXiv:1912.03821

Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances

Multi-agent reinforcement learning (MARL) has long been a significant and everlasting research topic in both machine learning and control. With the recent development of (single-agent) deep RL, there is a resurgence of interests in developing new MARL algorithms, especially those that are backed by theoretical analysis. In this paper, we review some recent advances a sub-area of this topic: decentralized MARL with networked agents. Specifically, multiple agents perform sequential decision-making in a common environment, without the coordination of any central controller. Instead, the agents are allowed to exchange information with their neighbors over a communication network. Such a setting finds broad applications in the control and operation of robots, unmanned vehicles, mobile sensor networks, and smart grid. This review is built upon several our research endeavors in this direction, together with some progresses made by other researchers along the line. We hope this review to inspire the devotion of more research efforts to this exciting yet challenging area.

arXiv:1912.03558공식 코드 · Papers with Code

Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery

Human players in professional team sports achieve high level coordination by dynamically choosing complementary skills and executing primitive actions to perform these skills. As a step toward creating intelligent agents with this capability for fully cooperative multi-agent settings, we propose a two-level hierarchical multi-agent reinforcement learning (MARL) algorithm with unsupervised skill discovery. Agents learn useful and distinct skills at the low level via independent Q-learning, while they learn to select complementary latent skill variables at the high level via centralized multi-agent training with an extrinsic team reward. The set of low-level skills emerges from an intrinsic reward that solely promotes the decodability of latent skill variables from the trajectory of a low-level skill, without the need for hand-crafted rewards for each skill. For scalable decentralized execution, each agent independently chooses latent skill variables and primitive actions based on local observations. Our overall method enables the use of general cooperative MARL algorithms for training high level policies and single-agent RL for training low level skills. Experiments on a stochastic high dimensional team game show the emergence of useful skills and cooperative team play. The interpretability of the learned skills show the promise of the proposed method for achieving human-AI cooperation in team sports games.

arXiv:1912.02288공식 코드 · Papers with Code

Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning

In recent years we have seen fast progress on a number of benchmark problems in AI, with modern methods achieving near or super human performance in Go, Poker and Dota. One common aspect of all of these challenges is that they are by design adversarial or, technically speaking, zero-sum. In contrast to these settings, success in the real world commonly requires humans to collaborate and communicate with others, in settings that are, at least partially, cooperative. In the last year, the card game Hanabi has been established as a new benchmark environment for AI to fill this gap. In particular, Hanabi is interesting to humans since it is entirely focused on theory of mind, i.e., the ability to effectively reason over the intentions, beliefs and point of view of other agents when observing their actions. Learning to be informative when observed by others is an interesting challenge for Reinforcement Learning (RL): Fundamentally, RL requires agents to explore in order to discover good policies. However, when done naively, this randomness will inherently make their actions less informative to others during training. We present a new deep multi-agent RL method, the Simplified Action Decoder (SAD), which resolves this contradiction exploiting the centralized training phase. During training SAD allows other agents to not only observe the (exploratory) action chosen, but agents instead also observe the greedy action of their team mates. By combining this simple intuition with best practices for multi-agent learning, SAD establishes a new SOTA for learning methods for 2-5 players on the self-play part of the Hanabi challenge. Our ablations show the contributions of SAD compared with the best practice components. All of our code and trained agents are available at https://github.com/facebookresearch/Hanabi_SAD.

arXiv:1912.01698

Online and Bandit Algorithms for Nonstationary Stochastic Saddle-Point Optimization

Saddle-point optimization problems are an important class of optimization problems with applications to game theory, multi-agent reinforcement learning and machine learning. A majority of the rich literature available for saddle-point optimization has focused on the offline setting. In this paper, we study nonstationary versions of stochastic, smooth, strongly-convex and strongly-concave saddle-point optimization problem, in both online (or first-order) and multi-point bandit (or zeroth-order) settings. We first propose natural notions of regret for such nonstationary saddle-point optimization problems. We then analyze extragradient and Frank-Wolfe algorithms, for the unconstrained and constrained settings respectively, for the above class of nonstationary saddle-point optimization problems. We establish sub-linear regret bounds on the proposed notions of regret in both the online and bandit setting.

arXiv:1912.01160

Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning

Social psychology and real experiences show that cognitive consistency plays an important role to keep human society in order: if people have a more consistent cognition about their environments, they are more likely to achieve better cooperation. Meanwhile, only cognitive consistency within a neighborhood matters because humans only interact directly with their neighbors. Inspired by these observations, we take the first step to introduce \emph{neighborhood cognitive consistency} (NCC) into multi-agent reinforcement learning (MARL). Our NCC design is quite general and can be easily combined with existing MARL methods. As examples, we propose neighborhood cognition consistent deep Q-learning and Actor-Critic to facilitate large-scale multi-agent cooperations. Extensive experiments on several challenging tasks (i.e., packet routing, wifi configuration, and Google football player control) justify the superior performance of our methods compared with state-of-the-art MARL approaches.

arXiv:1912.00949

Multi-Agent Deep Reinforcement Learning with Adaptive Policies

We propose a novel approach to address one aspect of the non-stationarity problem in multi-agent reinforcement learning (RL), where the other agents may alter their policies due to environment changes during execution. This violates the Markov assumption that governs most single-agent RL methods and is one of the key challenges in multi-agent RL. To tackle this, we propose to train multiple policies for each agent and postpone the selection of the best policy at execution time. Specifically, we model the environment non-stationarity with a finite set of scenarios and train policies fitting each scenario. In addition to multiple policies, each agent also learns a policy predictor to determine which policy is the best with its local information. By doing so, each agent is able to adapt its policy when the environment changes and consequentially the other agents alter their policies during execution. We empirically evaluated our method on a variety of common benchmark problems proposed for multi-agent deep RL in the literature. Our experimental results show that the agents trained by our algorithm have better adaptiveness in changing environments and outperform the state-of-the-art methods in all the tested environments.

arXiv:1912.00498

Optimization for Reinforcement Learning: From Single Agent to Cooperative Agents

This article reviews recent advances in multi-agent reinforcement learning algorithms for large-scale control systems and communication networks, which learn to communicate and cooperate. We provide an overview of this emerging field, with an emphasis on the decentralized setting under different coordination protocols. We highlight the evolution of reinforcement learning algorithms from single-agent to multi-agent systems, from a distributed optimization perspective, and conclude with future directions and challenges, in the hope to catalyze the growing synergy among distributed optimization, signal processing, and reinforcement learning communities.

arXiv:1911.11972

Adversarial Deep Reinforcement Learning based Adaptive Moving Target Defense

Moving target defense (MTD) is a proactive defense approach that aims to thwart attacks by continuously changing the attack surface of a system (e.g., changing host or network configurations), thereby increasing the adversary's uncertainty and attack cost. To maximize the impact of MTD, a defender must strategically choose when and what changes to make, taking into account both the characteristics of its system as well as the adversary's observed activities. Finding an optimal strategy for MTD presents a significant challenge, especially when facing a resourceful and determined adversary who may respond to the defender's actions. In this paper, we propose a multi-agent partially-observable Markov Decision Process model of MTD and formulate a two-player general-sum game between the adversary and the defender. Based on an established model of adaptive MTD, we propose a multi-agent reinforcement learning framework based on the double oracle algorithm to solve the game. In the experiments, we show the effectiveness of our framework in finding optimal policies.