PyTorchKR Papers

최신 논문

총 445편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2108.13976공식 코드 · Papers with Code

WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU

Deep reinforcement learning (RL) is a powerful framework to train decision-making models in complex environments. However, RL can be slow as it requires repeated interaction with a simulation of the environment. In particular, there are key system engineering bottlenecks when using RL in complex environments that feature multiple agents with high-dimensional state, observation, or action spaces. We present WarpDrive, a flexible, lightweight, and easy-to-use open-source RL framework that implements end-to-end deep multi-agent RL on a single GPU (Graphics Processing Unit), built on PyCUDA and PyTorch. Using the extreme parallelization capability of GPUs, WarpDrive enables orders-of-magnitude faster RL compared to common implementations that blend CPU simulations and GPU models. Our design runs simulations and the agents in each simulation in parallel. It eliminates data copying between CPU and GPU. It also uses a single simulation data store on the GPU that is safely updated in-place. WarpDrive provides a lightweight Python interface and flexible environment wrappers that are easy to use and extend. Together, this allows the user to easily run thousands of concurrent multi-agent simulations and train on extremely large batches of experience. Through extensive experiments, we verify that WarpDrive provides high-throughput and scales almost linearly to many agents and parallel environments. For example, WarpDrive yields 2.9 million environment steps/second with 2000 environments and 1000 agents (at least 100x higher throughput compared to a CPU implementation) in a benchmark Tag simulation. As such, WarpDrive is a fast and extensible multi-agent RL platform to significantly accelerate research and development.

arXiv:2108.00506공식 코드 · Papers with Code

Scalable Multi-agent Reinforcement Learning Algorithm for Wireless Networks

Scalability is the key roadstone towards the application of cooperative intelligent algorithms in large-scale networks. Reinforcement learning (RL) is known as model-free and high efficient intelligent algorithm for communication problems and proved useful in the communication network. However, when coming to large-scale networks with limited centralization, it is not possible to employ a centralized entity to perform joint real-time decision making for entire network. This introduces the scalability challenges, while multi-agent reinforcement shows the opportunity to cope this challenges and extend the intelligent algorithm to cooperative large-scale network. In this paper, we introduce the federated mean-field multi-agent reinforcement learning structure to capture the problem in large scale multi-agent communication scenarios, where agents share parameters to form consistency. We present the theoretical basis of our architecture and show the influence of federated frequency with an informational multi-agent model. We then exam the performance of our architecture with a coordinated multi-point environment which requires handshakes between neighbour access-points to realise the cooperation gain. Our result shows that the learning structure can effectively solve the cooperation problem in a large scale network with decent scalability. We also show the effectiveness of federated algorithms and highlight the importance of maintaining personality in each access-point.

arXiv:2107.14698공식 코드 · Papers with Code

Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learning

High sample complexity remains a barrier to the application of reinforcement learning (RL), particularly in multi-agent systems. A large body of work has demonstrated that exploration mechanisms based on the principle of optimism under uncertainty can significantly improve the sample efficiency of RL in single agent tasks. This work seeks to understand the role of optimistic exploration in non-cooperative multi-agent settings. We will show that, in zero-sum games, optimistic exploration can cause the learner to waste time sampling parts of the state space that are irrelevant to strategic play, as they can only be reached through cooperation between both players. To address this issue, we introduce a formal notion of strategically efficient exploration in Markov games, and use this to develop two strategically efficient learning algorithms for finite Markov games. We demonstrate that these methods can be significantly more sample efficient than their optimistic counterparts.

arXiv:2107.08295공식 코드 · Papers with Code

Communicating via Markov Decision Processes

We consider the problem of communicating exogenous information by means of Markov decision process trajectories. This setting, which we call a Markov coding game (MCG), generalizes both source coding and a large class of referential games. MCGs also isolate a problem that is important in decentralized control settings in which cheap-talk is not available -- namely, they require balancing communication with the associated cost of communicating. We contribute a theoretically grounded approach to MCGs based on maximum entropy reinforcement learning and minimum entropy coupling that we call MEME. Due to recent breakthroughs in approximation algorithms for minimum entropy coupling, MEME is not merely a theoretical algorithm, but can be applied to practical settings. Empirically, we show both that MEME is able to outperform a strong baseline on small MCGs and that MEME is able to achieve strong performance on extremely large MCGs. To the latter point, we demonstrate that MEME is able to losslessly communicate binary images via trajectories of Cartpole and Pong, while simultaneously achieving the maximal or near maximal expected returns, and that it is even capable of performing well in the presence of actuator noise.

arXiv:2107.01460공식 코드 · Papers with Code

Mava: a research library for distributed multi-agent reinforcement learning in JAX

Multi-agent reinforcement learning (MARL) research is inherently computationally expensive and it is often difficult to obtain a sufficient number of experiment samples to test hypotheses and make robust statistical claims. Furthermore, MARL algorithms are typically complex in their design and can be tricky to implement correctly. These aspects of MARL present a difficult challenge when it comes to creating useful software for advanced research. Our criteria for such software is that it should be simple enough to use to implement new ideas quickly, while at the same time be scalable and fast enough to test those ideas in a reasonable amount of time. In this preliminary technical report, we introduce Mava, a research library for MARL written purely in JAX, that aims to fulfill these criteria. We discuss the design and core features of Mava, and demonstrate its use and performance across a variety of environments. In particular, we show Mava's substantial speed advantage, with improvements of 10-100x compared to other popular MARL frameworks, while maintaining strong performance. This allows for researchers to test ideas in a few minutes instead of several hours. Finally, Mava forms part of an ecosystem of libraries that seamlessly integrate with each other to help facilitate advanced research in MARL. We hope Mava will benefit the community and help drive scientifically sound and statistically robust research in the field. The open-source repository for Mava is available at https://github.com/instadeepai/Mava.

arXiv:2107.01151공식 코드 · Papers with Code

Collaborative Visual Navigation

As a fundamental problem for Artificial Intelligence, multi-agent system (MAS) is making rapid progress, mainly driven by multi-agent reinforcement learning (MARL) techniques. However, previous MARL methods largely focused on grid-world like or game environments; MAS in visually rich environments has remained less explored. To narrow this gap and emphasize the crucial role of perception in MAS, we propose a large-scale 3D dataset, CollaVN, for multi-agent visual navigation (MAVN). In CollaVN, multiple agents are entailed to cooperatively navigate across photo-realistic environments to reach target locations. Diverse MAVN variants are explored to make our problem more general. Moreover, a memory-augmented communication framework is proposed. Each agent is equipped with a private, external memory to persistently store communication information. This allows agents to make better use of their past communication information, enabling more efficient collaboration and robust long-term planning. In our experiments, several baselines and evaluation metrics are designed. We also empirically verify the efficacy of our proposed MARL approach across different MAVN task settings.

arXiv:2106.07551공식 코드 · Papers with Code

MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning

Population-based multi-agent reinforcement learning (PB-MARL) refers to the series of methods nested with reinforcement learning (RL) algorithms, which produces a self-generated sequence of tasks arising from the coupled population dynamics. By leveraging auto-curricula to induce a population of distinct emergent strategies, PB-MARL has achieved impressive success in tackling multi-agent tasks. Despite remarkable prior arts of distributed RL frameworks, PB-MARL poses new challenges for parallelizing the training frameworks due to the additional complexity of multiple nested workloads between sampling, training and evaluation involved with heterogeneous policy interactions. To solve these problems, we present MALib, a scalable and efficient computing framework for PB-MARL. Our framework is comprised of three key components: (1) a centralized task dispatching model, which supports the self-generated tasks and scalable training with heterogeneous policy combinations; (2) a programming architecture named Actor-Evaluator-Learner, which achieves high parallelism for both training and sampling, and meets the evaluation requirement of auto-curriculum learning; (3) a higher-level abstraction of MARL training paradigms, which enables efficient code reuse and flexible deployments on different distributed computing paradigms. Experiments on a series of complex tasks such as multi-agent Atari Games show that MALib achieves throughput higher than 40K FPS on a single machine with $32$ CPU cores; 5x speedup than RLlib and at least 3x speedup than OpenSpiel in multi-agent training tasks. MALib is publicly available at https://github.com/sjtu-marl/malib.

arXiv:2106.06828공식 코드 · Papers with Code

A Game-Theoretic Approach to Multi-Agent Trust Region Optimization

Trust region methods are widely applied in single-agent reinforcement learning problems due to their monotonic performance-improvement guarantee at every iteration. Nonetheless, when applied in multi-agent settings, the guarantee of trust region methods no longer holds because an agent's payoff is also affected by other agents' adaptive behaviors. To tackle this problem, we conduct a game-theoretical analysis in the policy space, and propose a multi-agent trust region learning method (MATRL), which enables trust region optimization for multi-agent learning. Specifically, MATRL finds a stable improvement direction that is guided by the solution concept of Nash equilibrium at the meta-game level. We derive the monotonic improvement guarantee in multi-agent settings and empirically show the local convergence of MATRL to stable fixed points in the two-player rotational differential game. To test our method, we evaluate MATRL in both discrete and continuous multiplayer general-sum games including checker and switch grid worlds, multi-agent MuJoCo, and Atari games. Results suggest that MATRL significantly outperforms strong multi-agent reinforcement learning baselines.

arXiv:2106.06613공식 코드 · Papers with Code

A New Formalism, Method and Open Issues for Zero-Shot Coordination

In many coordination problems, independently reasoning humans are able to discover mutually compatible policies. In contrast, independently trained self-play policies are often mutually incompatible. Zero-shot coordination (ZSC) has recently been proposed as a new frontier in multi-agent reinforcement learning to address this fundamental issue. Prior work approaches the ZSC problem by assuming players can agree on a shared learning algorithm but not on labels for actions and observations, and proposes other-play as an optimal solution. However, until now, this "label-free" problem has only been informally defined. We formalize this setting as the label-free coordination (LFC) problem by defining the label-free coordination game. We show that other-play is not an optimal solution to the LFC problem as it fails to consistently break ties between incompatible maximizers of the other-play objective. We introduce an extension of the algorithm, other-play with tie-breaking, and prove that it is optimal in the LFC problem and an equilibrium in the LFC game. Since arbitrary tie-breaking is precisely what the ZSC setting aims to prevent, we conclude that the LFC problem does not reflect the aims of ZSC. To address this, we introduce an alternative informal operationalization of ZSC as a starting point for future work.

arXiv:2106.06224공식 코드 · Papers with Code

A Cooperative-Competitive Multi-Agent Framework for Auto-bidding in Online Advertising

In online advertising, auto-bidding has become an essential tool for advertisers to optimize their preferred ad performance metrics by simply expressing high-level campaign objectives and constraints. Previous works designed auto-bidding tools from the view of single-agent, without modeling the mutual influence between agents. In this paper, we instead consider this problem from a distributed multi-agent perspective, and propose a general $\underline{M}$ulti-$\underline{A}$gent reinforcement learning framework for $\underline{A}$uto-$\underline{B}$idding, namely MAAB, to learn the auto-bidding strategies. First, we investigate the competition and cooperation relation among auto-bidding agents, and propose a temperature-regularized credit assignment to establish a mixed cooperative-competitive paradigm. By carefully making a competition and cooperation trade-off among agents, we can reach an equilibrium state that guarantees not only individual advertiser's utility but also the system performance (i.e., social welfare). Second, to avoid the potential collusion behaviors of bidding low prices underlying the cooperation, we further propose bar agents to set a personalized bidding bar for each agent, and then alleviate the revenue degradation due to the cooperation. Third, to deploy MAAB in the large-scale advertising system with millions of advertisers, we propose a mean-field approach. By grouping advertisers with the same objective as a mean auto-bidding agent, the interactions among the large-scale advertisers are greatly simplified, making it practical to train MAAB efficiently. Extensive experiments on the offline industrial dataset and Alibaba advertising platform demonstrate that our approach outperforms several baseline methods in terms of social welfare and revenue.

arXiv:2106.06135공식 코드 · Papers with Code

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents. While significant achievements have been made in various perfect- and imperfect-information games, DouDizhu (a.k.a. Fighting the Landlord), a three-player card game, is still unsolved. DouDizhu is a very challenging domain with competition, collaboration, imperfect information, large state space, and particularly a massive set of possible actions where the legal actions vary significantly from turn to turn. Unfortunately, modern reinforcement learning algorithms mainly focus on simple and small action spaces, and not surprisingly, are shown not to make satisfactory progress in DouDizhu. In this work, we propose a conceptually simple yet effective DouDizhu AI system, namely DouZero, which enhances traditional Monte-Carlo methods with deep neural networks, action encoding, and parallel actors. Starting from scratch in a single server with four GPUs, DouZero outperformed all the existing DouDizhu AI programs in days of training and was ranked the first in the Botzone leaderboard among 344 AI agents. Through building DouZero, we show that classic Monte-Carlo methods can be made to deliver strong results in a hard domain with a complex action space. The code and an online demo are released at https://github.com/kwai/DouZero with the hope that this insight could motivate future work.

arXiv:2106.05492공식 코드 · Papers with Code

Learning to Play General-Sum Games Against Multiple Boundedly Rational Agents

We study the problem of training a principal in a multi-agent general-sum game using reinforcement learning (RL). Learning a robust principal policy requires anticipating the worst possible strategic responses of other agents, which is generally NP-hard. However, we show that no-regret dynamics can identify these worst-case responses in poly-time in smooth games. We propose a framework that uses this policy evaluation method for efficiently learning a robust principal policy using RL. This framework can be extended to provide robustness to boundedly rational agents too. Our motivating application is automated mechanism design: we empirically demonstrate our framework learns robust mechanisms in both matrix games and complex spatiotemporal games. In particular, we learn a dynamic tax policy that improves the welfare of a simulated trade-and-barter economy by 15%, even when facing previously unseen boundedly rational RL taxpayers.

arXiv:2106.02745공식 코드 · Papers with Code

Neural Auto-Curricula

When solving two-player zero-sum games, multi-agent reinforcement learning (MARL) algorithms often create populations of agents where, at each iteration, a new agent is discovered as the best response to a mixture over the opponent population. Within such a process, the update rules of "who to compete with" (i.e., the opponent mixture) and "how to beat them" (i.e., finding best responses) are underpinned by manually developed game theoretical principles such as fictitious play and Double Oracle. In this paper, we introduce a novel framework -- Neural Auto-Curricula (NAC) -- that leverages meta-gradient descent to automate the discovery of the learning update rule without explicit human design. Specifically, we parameterise the opponent selection module by neural networks and the best-response module by optimisation subroutines, and update their parameters solely via interaction with the game engine, where both players aim to minimise their exploitability. Surprisingly, even without human design, the discovered MARL algorithms achieve competitive or even better performance with the state-of-the-art population-based game solvers (e.g., PSRO) on Games of Skill, differentiable Lotto, non-transitive Mixture Games, Iterated Matching Pennies, and Kuhn Poker. Additionally, we show that NAC is able to generalise from small games to large games, for example training on Kuhn Poker and outperforming PSRO on Leduc Poker. Our work inspires a promising future direction to discover general MARL algorithms solely from data.

arXiv:2106.03400공식 코드 · Papers with Code

Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning

Learning from datasets without interaction with environments (Offline Learning) is an essential step to apply Reinforcement Learning (RL) algorithms in real-world scenarios. However, compared with the single-agent counterpart, offline multi-agent RL introduces more agents with the larger state and action space, which is more challenging but attracts little attention. We demonstrate current offline RL algorithms are ineffective in multi-agent systems due to the accumulated extrapolation error. In this paper, we propose a novel offline RL algorithm, named Implicit Constraint Q-learning (ICQ), which effectively alleviates the extrapolation error by only trusting the state-action pairs given in the dataset for value estimation. Moreover, we extend ICQ to multi-agent tasks by decomposing the joint-policy under the implicit constraint. Experimental results demonstrate that the extrapolation error is successfully controlled within a reasonable range and insensitive to the number of agents. We further show that ICQ achieves the state-of-the-art performance in the challenging multi-agent offline tasks (StarCraft II). Our code is public online at https://github.com/YiqinYang/ICQ.

arXiv:2105.15013공식 코드 · Papers with Code

SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning

Value factorisation is a useful technique for multi-agent reinforcement learning (MARL) in global reward game, however its underlying mechanism is not yet fully understood. This paper studies a theoretical framework for value factorisation with interpretability via Shapley value theory. We generalise Shapley value to Markov convex game called Markov Shapley value (MSV) and apply it as a value factorisation method in global reward game, which is obtained by the equivalence between the two games. Based on the properties of MSV, we derive Shapley-Bellman optimality equation (SBOE) to evaluate the optimal MSV, which corresponds to an optimal joint deterministic policy. Furthermore, we propose Shapley-Bellman operator (SBO) that is proved to solve SBOE. With a stochastic approximation and some transformations, a new MARL algorithm called Shapley Q-learning (SHAQ) is established, the implementation of which is guided by the theoretical results of SBO and MSV. We also discuss the relationship between SHAQ and relevant value factorisation methods. In the experiments, SHAQ exhibits not only superior performances on all tasks but also the interpretability that agrees with the theoretical analysis. The implementation of this paper is on https://github.com/hsvgbkhgbv/shapley-q-learning.

arXiv:2105.12196공식 코드 · Papers with Code

From Motor Control to Team Play in Simulated Humanoid Football

Intelligent behaviour in the physical world exhibits structure at multiple spatial and temporal scales. Although movements are ultimately executed at the level of instantaneous muscle tensions or joint torques, they must be selected to serve goals defined on much longer timescales, and in terms of relations that extend far beyond the body itself, ultimately involving coordination with other agents. Recent research in artificial intelligence has shown the promise of learning-based approaches to the respective problems of complex movement, longer-term planning and multi-agent coordination. However, there is limited research aimed at their integration. We study this problem by training teams of physically simulated humanoid avatars to play football in a realistic virtual environment. We develop a method that combines imitation learning, single- and multi-agent reinforcement learning and population-based training, and makes use of transferable representations of behaviour for decision making at different levels of abstraction. In a sequence of stages, players first learn to control a fully articulated body to perform realistic, human-like movements such as running and turning; they then acquire mid-level football skills such as dribbling and shooting; finally, they develop awareness of others and play as a team, bridging the gap between low-level motor control at a timescale of milliseconds, and coordinated goal-directed behaviour as a team at the timescale of tens of seconds. We investigate the emergence of behaviours at different levels of abstraction, as well as the representations that underlie these behaviours using several analysis techniques, including statistics from real-world sports analytics. Our work constitutes a complete demonstration of integrated decision-making at multiple scales in a physically embodied multi-agent setting. See project video at https://youtu.be/KHMwq9pv7mg.

arXiv:2105.08692공식 코드 · Papers with Code

Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition

In real-world multi-agent systems, agents with different capabilities may join or leave without altering the team's overarching goals. Coordinating teams with such dynamic composition is challenging: the optimal team strategy varies with the composition. We propose COPA, a coach-player framework to tackle this problem. We assume the coach has a global view of the environment and coordinates the players, who only have partial views, by distributing individual strategies. Specifically, we 1) adopt the attention mechanism for both the coach and the players; 2) propose a variational objective to regularize learning; and 3) design an adaptive communication method to let the coach decide when to communicate with the players. We validate our methods on a resource collection task, a rescue game, and the StarCraft micromanagement tasks. We demonstrate zero-shot generalization to new team compositions. Our method achieves comparable or better performance than the setting where all players have a full view of the environment. Moreover, we see that the performance remains high even when the coach communicates as little as 13% of the time using the adaptive communication strategy.

arXiv:2105.03363공식 코드 · Papers with Code

Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts

This paper investigates the model-based methods in multi-agent reinforcement learning (MARL). We specify the dynamics sample complexity and the opponent sample complexity in MARL, and conduct a theoretic analysis of return discrepancy upper bound. To reduce the upper bound with the intention of low sample complexity during the whole learning process, we propose a novel decentralized model-based MARL method, named Adaptive Opponent-wise Rollout Policy Optimization (AORPO). In AORPO, each agent builds its multi-agent environment model, consisting of a dynamics model and multiple opponent models, and trains its policy with the adaptive opponent-wise rollout. We further prove the theoretic convergence of AORPO under reasonable assumptions. Empirical experiments on competitive and cooperative tasks demonstrate that AORPO can achieve improved sample efficiency with comparable asymptotic performance over the compared MARL methods.

arXiv:2104.06655공식 코드 · Papers with Code

Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning

Deep reinforcement learning methods have shown great performance on many challenging cooperative multi-agent tasks. Two main promising research directions are multi-agent value function decomposition and multi-agent policy gradients. In this paper, we propose a new decomposed multi-agent soft actor-critic (mSAC) method, which effectively combines the advantages of the aforementioned two methods. The main modules include decomposed Q network architecture, discrete probabilistic policy and counterfactual advantage function (optinal). Theoretically, mSAC supports efficient off-policy learning and addresses credit assignment problem partially in both discrete and continuous action spaces. Tested on StarCraft II micromanagement cooperative multiagent benchmark, we empirically investigate the performance of mSAC against its variants and analyze the effects of the different components. Experimental results demonstrate that mSAC significantly outperforms policy-based approach COMA, and achieves competitive results with SOTA value-based approach Qmix on most tasks in terms of asymptotic perfomance metric. In addition, mSAC achieves pretty good results on large action space tasks, such as 2c_vs_64zg and MMM2.

arXiv:2104.05610공식 코드 · Papers with Code

A coevolutionary approach to deep multi-agent reinforcement learning

Traditionally, Deep Artificial Neural Networks (DNN's) are trained through gradient descent. Recent research shows that Deep Neuroevolution (DNE) is also capable of evolving multi-million-parameter DNN's, which proved to be particularly useful in the field of Reinforcement Learning (RL). This is mainly due to its excellent scalability and simplicity compared to the traditional MDP-based RL methods. So far, DNE has only been applied to complex single-agent problems. As evolutionary methods are a natural choice for multi-agent problems, the question arises whether DNE can also be applied in a complex multi-agent setting. In this paper, we describe and validate a new approach based on Coevolution. To validate our approach, we benchmark two Deep Coevolutionary Algorithms on a range of multi-agent Atari games and compare our results against the results of Ape-X DQN. Our results show that these Deep Coevolutionary algorithms (1) can be successfully trained to play various games, (2) outperform Ape-X DQN in some of them, and therefore (3) show that Coevolution can be a viable approach to solving complex multi-agent decision-making problems.