PyTorchKR Papers

최신 논문

총 1,869편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2204.12568

Toward Policy Explanations for Multi-Agent Reinforcement Learning

Advances in multi-agent reinforcement learning (MARL) enable sequential decision making for a range of exciting multi-agent applications such as cooperative AI and autonomous driving. Explaining agent decisions is crucial for improving system transparency, increasing user satisfaction, and facilitating human-agent collaboration. However, existing works on explainable reinforcement learning mostly focus on the single-agent setting and are not suitable for addressing challenges posed by multi-agent environments. We present novel methods to generate two types of policy explanations for MARL: (i) policy summarization about the agent cooperation and task sequence, and (ii) language explanations to answer queries about agent behavior. Experimental results on three MARL domains demonstrate the scalability of our methods. A user study shows that the generated explanations significantly improve user performance and increase subjective ratings on metrics such as user satisfaction.

arXiv:2204.12190공식 코드 · Papers with Code

Multi-Agent Reinforcement Learning for Traffic Signal Control through Universal Communication Method

How to coordinate the communication among intersections effectively in real complex traffic scenarios with multi-intersection is challenging. Existing approaches only enable the communication in a heuristic manner without considering the content/importance of information to be shared. In this paper, we propose a universal communication form UniComm between intersections. UniComm embeds massive observations collected at one agent into crucial predictions of their impact on its neighbors, which improves the communication efficiency and is universal across existing methods. We also propose a concise network UniLight to make full use of communications enabled by UniComm. Experimental results on real datasets demonstrate that UniComm universally improves the performance of existing state-of-the-art methods, and UniLight significantly outperforms existing methods on a wide range of traffic situations.

arXiv:2204.12064

PP-MARL: Efficient Privacy-Preserving Multi-Agent Reinforcement Learning for Cooperative Intelligence in Communications

Cooperative intelligence (CI) is expected to become an integral element in next-generation networks because it can aggregate the capabilities and intelligence of multiple devices. Multi-agent reinforcement learning (MARL) is a popular approach for achieving CI in communication problems by enabling effective collaboration among agents to address sequential problems. However, ensuring privacy protection for MARL is a challenging task because of the presence of heterogeneous agents that learn interdependently via sharing information. Implementing privacy protection techniques such as data encryption and federated learning to MARL introduces the notable overheads (e.g., computation and bandwidth). To overcome these challenges, we propose PP-MARL, an efficient privacy-preserving learning scheme for MARL. PP-MARL leverages homomorphic encryption (HE) and differential privacy (DP) to protect privacy, while introducing split learning to decrease overheads via reducing the volume of shared messages, and then improve efficiency. We apply and evaluate PP-MARL in two communication-related use cases. Simulation results reveal that PP-MARL can achieve efficient and reliable collaboration with 1.1-6 times better privacy protection and lower overheads (e.g., 84-91% reduction in bandwidth) than state-of-the-art approaches.

arXiv:2204.11350

Collaborative Auto-Curricula Multi-Agent Reinforcement Learning with Graph Neural Network Communication Layer for Open-ended Wildfire-Management Resource Distribution

Most real-world domains can be formulated as multi-agent (MA) systems. Intentionality sharing agents can solve more complex tasks by collaborating, possibly in less time. True cooperative actions are beneficial for egoistic and collective reasons. However, teaching individual agents to sacrifice egoistic benefits for a better collective performance seems challenging. We build on a recently proposed Multi-Agent Reinforcement Learning (MARL) mechanism with a Graph Neural Network (GNN) communication layer. Rarely chosen communication actions were marginally beneficial. Here we propose a MARL system in which agents can help collaborators perform better while risking low individual performance. We conduct our study in the context of resource distribution for wildfire management. Communicating environmental features and partially observable fire occurrence help the agent collective to pre-emptively distribute resources. Furthermore, we introduce a procedural training environment accommodating auto-curricula and open-endedness towards better generalizability. Our MA communication proposal outperforms a Greedy Heuristic Baseline and a Single-Agent (SA) setup. We further demonstrate how auto-curricula and openendedness improves generalizability of our MA proposal.

arXiv:2204.09801

Exact Formulas for Finite-Time Estimation Errors of Decentralized Temporal Difference Learning with Linear Function Approximation

In this paper, we consider the policy evaluation problem in multi-agent reinforcement learning (MARL) and derive exact closed-form formulas for the finite-time mean-squared estimation errors of decentralized temporal difference (TD) learning with linear function approximation. Our analysis hinges upon the fact that the decentralized TD learning method can be viewed as a Markov jump linear system (MJLS). Then standard MJLS theory can be applied to quantify the mean and covariance matrix of the estimation error of the decentralized TD method at every time step. Various implications of our exact formulas on the algorithm performance are also discussed. An interesting finding is that under a necessary and sufficient stability condition, the mean-squared TD estimation error will converge to an exact limit at a specific exponential rate.

arXiv:2204.10063

Resilient robot teams: a review integrating decentralised control, change-detection, and learning

Purpose of review: This paper reviews opportunities and challenges for decentralised control, change-detection, and learning in the context of resilient robot teams. Recent findings: Exogenous fault detection methods can provide a generic detection or a specific diagnosis with a recovery solution. Robot teams can perform active and distributed sensing for detecting changes in the environment, including identifying and tracking dynamic anomalies, as well as collaboratively mapping dynamic environments. Resilient methods for decentralised control have been developed in learning perception-action-communication loops, multi-agent reinforcement learning, embodied evolution, offline evolution with online adaptation, explicit task allocation, and stigmergy in swarm robotics. Summary: Remaining challenges for resilient robot teams are integrating change-detection and trial-and-error learning methods, obtaining reliable performance evaluations under constrained evaluation time, improving the safety of resilient robot teams, theoretical results demonstrating rapid adaptation to given environmental perturbations, and designing realistic and compelling case studies.

arXiv:2204.09602

Federated Learning for Distributed Energy-Efficient Resource Allocation

In cellular networks, resource allocation is performed in a centralized way, which brings huge computation complexity to the base station (BS) and high transmission overhead. This paper investigates the distributed resource allocation scheme for cellular networks to maximize the energy efficiency of the system in the uplink transmission, while guaranteeing the quality of service (QoS) for cellular users. Particularly, to cope the fast varying channels in wireless communication environment, we propose a robust federated reinforcement learning (FRL_suc) framework to enable local users to perform distributed resource allocation in items of transmit power and channel assignment by the guidance of the local neural network trained at each user. Analysis and numerical results show that the proposed FRL_suc framework can lower the transmission overhead and offload the computation from the central server to the local users, while outperforming the conventional multi-agent reinforcement learning algorithm in terms of EE, and is more robust to channel variations.

arXiv:2204.09418

Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning

Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is tough to learn the model of the environment. The significant compounding error may hinder the learning process when model-based methods are applied to multi-agent tasks. This paper proposes an implicit model-based multi-agent reinforcement learning method based on value decomposition methods. Under this method, agents can interact with the learned virtual environment and evaluate the current state value according to imagined future states in the latent space, making agents have the foresight. Our approach can be applied to any multi-agent value decomposition method. The experimental results show that our method improves the sample efficiency in different partially observable Markov decision process domains.

arXiv:2204.07932

Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning

While deep neural networks (DNNs) have strengthened the performance of cooperative multi-agent reinforcement learning (c-MARL), the agent policy can be easily perturbed by adversarial examples. Considering the safety critical applications of c-MARL, such as traffic management, power management and unmanned aerial vehicle control, it is crucial to test the robustness of c-MARL algorithm before it was deployed in reality. Existing adversarial attacks for MARL could be used for testing, but is limited to one robustness aspects (e.g., reward, state, action), while c-MARL model could be attacked from any aspect. To overcome the challenge, we propose MARLSafe, the first robustness testing framework for c-MARL algorithms. First, motivated by Markov Decision Process (MDP), MARLSafe consider the robustness of c-MARL algorithms comprehensively from three aspects, namely state robustness, action robustness and reward robustness. Any c-MARL algorithm must simultaneously satisfy these robustness aspects to be considered secure. Second, due to the scarceness of c-MARL attack, we propose c-MARL attacks as robustness testing algorithms from multiple aspects. Experiments on \textit{SMAC} environment reveals that many state-of-the-art c-MARL algorithms are of low robustness in all aspect, pointing out the urgent need to test and enhance robustness of c-MARL algorithms.

arXiv:2204.05669

An Analysis of Discretization Methods for Communication Learning with Multi-Agent Reinforcement Learning

Communication is crucial in multi-agent reinforcement learning when agents are not able to observe the full state of the environment. The most common approach to allow learned communication between agents is the use of a differentiable communication channel that allows gradients to flow between agents as a form of feedback. However, this is challenging when we want to use discrete messages to reduce the message size since gradients cannot flow through a discrete communication channel. Previous work proposed methods to deal with this problem. However, these methods are tested in different communication learning architectures and environments, making it hard to compare them. In this paper, we compare several state-of-the-art discretization methods as well as two methods that have not been used for communication learning before. We do this comparison in the context of communication learning using gradients from other agents and perform tests on several environments. Our results show that none of the methods is best in all environments. The best choice in discretization method greatly depends on the environment. However, the discretize regularize unit (DRU), straight through DRU and the straight through gumbel softmax show the most consistent results across all the tested environments. Therefore, these methods prove to be the best choice for general use while the straight through estimator and the gumbel softmax may provide better results in specific environments but fail completely in others.

arXiv:2204.05576

Multi-agent Actor-Critic with Time Dynamical Opponent Model

In multi-agent reinforcement learning, multiple agents learn simultaneously while interacting with a common environment and each other. Since the agents adapt their policies during learning, not only the behavior of a single agent becomes non-stationary, but also the environment as perceived by the agent. This renders it particularly challenging to perform policy improvement. In this paper, we propose to exploit the fact that the agents seek to improve their expected cumulative reward and introduce a novel \textit{Time Dynamical Opponent Model} (TDOM) to encode the knowledge that the opponent policies tend to improve over time. We motivate TDOM theoretically by deriving a lower bound of the log objective of an individual agent and further propose \textit{Multi-Agent Actor-Critic with Time Dynamical Opponent Model} (TDOM-AC). We evaluate the proposed TDOM-AC on a differential game and the Multi-agent Particle Environment. We show empirically that TDOM achieves superior opponent behavior prediction during test time. The proposed TDOM-AC methodology outperforms state-of-the-art Actor-Critic methods on the performed experiments in cooperative and \textbf{especially} in mixed cooperative-competitive environments. TDOM-AC results in a more stable training and a faster convergence.

arXiv:2204.03991

The Complexity of Markov Equilibrium in Stochastic Games

We show that computing approximate stationary Markov coarse correlated equilibria (CCE) in general-sum stochastic games is computationally intractable, even when there are two players, the game is turn-based, the discount factor is an absolute constant, and the approximation is an absolute constant. Our intractability results stand in sharp contrast to normal-form games where exact CCEs are efficiently computable. A fortiori, our results imply that there are no efficient algorithms for learning stationary Markov CCE policies in multi-agent reinforcement learning (MARL), even when the interaction is two-player and turn-based, and both the discount factor and the desired approximation of the learned policies is an absolute constant. In turn, these results stand in sharp contrast to single-agent reinforcement learning (RL) where near-optimal stationary Markov policies can be efficiently learned. Complementing our intractability results for stationary Markov CCEs, we provide a decentralized algorithm (assuming shared randomness among players) for learning a nonstationary Markov CCE policy with polynomial time and sample complexity in all problem parameters. Previous work for learning Markov CCE policies all required exponential time and sample complexity in the number of players.

arXiv:2204.03516

Distributed Reinforcement Learning for Robot Teams: A Review

Purpose of review: Recent advances in sensing, actuation, and computation have opened the door to multi-robot systems consisting of hundreds/thousands of robots, with promising applications to automated manufacturing, disaster relief, harvesting, last-mile delivery, port/airport operations, or search and rescue. The community has leveraged model-free multi-agent reinforcement learning (MARL) to devise efficient, scalable controllers for multi-robot systems (MRS). This review aims to provide an analysis of the state-of-the-art in distributed MARL for multi-robot cooperation. Recent findings: Decentralized MRS face fundamental challenges, such as non-stationarity and partial observability. Building upon the "centralized training, decentralized execution" paradigm, recent MARL approaches include independent learning, centralized critic, value decomposition, and communication learning approaches. Cooperative behaviors are demonstrated through AI benchmarks and fundamental real-world robotic capabilities such as multi-robot motion/path planning. Summary: This survey reports the challenges surrounding decentralized model-free MARL for multi-robot cooperation and existing classes of approaches. We present benchmarks and robotic applications along with a discussion on current open avenues for research.

arXiv:2204.02268공식 코드 · Papers with Code

Learning to Bid Long-Term: Multi-Agent Reinforcement Learning with Long-Term and Sparse Reward in Repeated Auction Games

We propose a multi-agent distributed reinforcement learning algorithm that balances between potentially conflicting short-term reward and sparse, delayed long-term reward, and learns with partial information in a dynamic environment. We compare different long-term rewards to incentivize the algorithm to maximize individual payoff and overall social welfare. We test the algorithm in two simulated auction games, and demonstrate that 1) our algorithm outperforms two benchmark algorithms in a direct competition, with cost to social welfare, and 2) our algorithm's aggressive competitive behavior can be guided with the long-term reward signal to maximize both individual payoff and overall social welfare.

arXiv:2204.02013

RL4ReAl: Reinforcement Learning for Register Allocation

We aim to automate decades of research and experience in register allocation, leveraging machine learning. We tackle this problem by embedding a multi-agent reinforcement learning algorithm within LLVM, training it with the state of the art techniques. We formalize the constraints that precisely define the problem for a given instruction-set architecture, while ensuring that the generated code preserves semantic correctness. We also develop a gRPC based framework providing a modular and efficient compiler interface for training and inference. Our approach is architecture independent: we show experimental results targeting Intel x86 and ARM AArch64. Our results match or out-perform the heavily tuned, production-grade register allocators of LLVM.

arXiv:2204.01597

Optimising Energy Efficiency in UAV-Assisted Networks using Deep Reinforcement Learning

In this letter, we study the energy efficiency (EE) optimisation of unmanned aerial vehicles (UAVs) providing wireless coverage to static and mobile ground users. Recent multi-agent reinforcement learning approaches optimise the system's EE using a 2D trajectory design, neglecting interference from nearby UAV cells. We aim to maximise the system's EE by jointly optimising each UAV's 3D trajectory, number of connected users, and the energy consumed, while accounting for interference. Thus, we propose a cooperative Multi-Agent Decentralised Double Deep Q-Network (MAD-DDQN) approach. Our approach outperforms existing baselines in terms of EE by as much as 55 -- 80%.

arXiv:2203.15925

Asynchronous, Option-Based Multi-Agent Policy Gradient: A Conditional Reasoning Approach

Cooperative multi-agent problems often require coordination between agents, which can be achieved through a centralized policy that considers the global state. Multi-agent policy gradient (MAPG) methods are commonly used to learn such policies, but they are often limited to problems with low-level action spaces. In complex problems with large state and action spaces, it is advantageous to extend MAPG methods to use higher-level actions, also known as options, to improve the policy search efficiency. However, multi-robot option executions are often asynchronous, that is, agents may select and complete their options at different time steps. This makes it difficult for MAPG methods to derive a centralized policy and evaluate its gradient, as centralized policy always select new options at the same time. In this work, we propose a novel, conditional reasoning approach to address this problem and demonstrate its effectiveness on representative option-based multi-agent cooperative tasks through empirical validation. Find code and videos at: \href{https://sites.google.com/view/mahrlsupp/}{https://sites.google.com/view/mahrlsupp/}

arXiv:2203.14152

Collaborative Intelligent Reflecting Surface Networks with Multi-Agent Reinforcement Learning

Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks. In this paper, we investigate a multi-user communication system assisted by cooperative IRS devices with the capability of energy harvesting. Aiming to maximize the long-term average achievable system rate, an optimization problem is formulated by jointly designing the transmit beamforming at the base station (BS) and discrete phase shift beamforming at the IRSs, with the constraints on transmit power, user data rate requirement and IRS energy buffer size. Considering time-varying channels and stochastic arrivals of energy harvested by the IRSs, we first formulate the problem as a Markov decision process (MDP) and then develop a novel multi-agent Q-mix (MAQ) framework with two layers to decouple the optimization parameters. The higher layer is for optimizing phase shift resolutions, and the lower one is for phase shift beamforming and power allocation. Since the phase shift optimization is an integer programming problem with a large-scale action space, we improve MAQ by incorporating the Wolpertinger method, namely, MAQ-WP algorithm to achieve a sub-optimality with reduced dimensions of action space. In addition, as MAQ-WP is still of high complexity to achieve good performance, we propose a policy gradient-based MAQ algorithm, namely, MAQ-PG, by mapping the discrete phase shift actions into a continuous space at the cost of a slight performance loss. Simulation results demonstrate that the proposed MAQ-WP and MAQ-PG algorithms can converge faster and achieve data rate improvements of 10.7% and 8.8% over the conventional multi-agent DDPG, respectively.

arXiv:2203.13319

Remember and Forget Experience Replay for Multi-Agent Reinforcement Learning

We present the extension of the Remember and Forget for Experience Replay (ReF-ER) algorithm to Multi-Agent Reinforcement Learning (MARL). ReF-ER was shown to outperform state of the art algorithms for continuous control in problems ranging from the OpenAI Gym to complex fluid flows. In MARL, the dependencies between the agents are included in the state-value estimator and the environment dynamics are modeled via the importance weights used by ReF-ER. In collaborative environments, we find the best performance when the value is estimated using individual rewards and we ignore the effects of other actions on the transition map. We benchmark the performance of ReF-ER MARL on the Stanford Intelligent Systems Laboratory (SISL) environments. We find that employing a single feed-forward neural network for the policy and the value function in ReF-ER MARL, outperforms state of the art algorithms that rely on complex neural network architectures.

arXiv:2203.10603

Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects

Significant advances have recently been achieved in Multi-Agent Reinforcement Learning (MARL) which tackles sequential decision-making problems involving multiple participants. However, MARL requires a tremendous number of samples for effective training. On the other hand, model-based methods have been shown to achieve provable advantages of sample efficiency. However, the attempts of model-based methods to MARL have just started very recently. This paper presents a review of the existing research on model-based MARL, including theoretical analyses, algorithms, and applications, and analyzes the advantages and potential of model-based MARL. Specifically, we provide a detailed taxonomy of the algorithms and point out the pros and cons for each algorithm according to the challenges inherent to multi-agent scenarios. We also outline promising directions for future development of this field.