PyTorchKR Papers

최신 논문

총 1,869편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2112.06127

Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings

Building upon prior research that highlighted the need for standardizing environments for building control research, and inspired by recently introduced challenges for real life reinforcement learning control, here we propose a non-exhaustive set of nine real world challenges for reinforcement learning control in grid-interactive buildings. We argue that research in this area should be expressed in this framework in addition to providing a standardized environment for repeatability. Advanced controllers such as model predictive control and reinforcement learning (RL) control have both advantages and disadvantages that prevent them from being implemented in real world problems. Comparisons between the two are rare, and often biased. By focusing on the challenges, we can investigate the performance of the controllers under a variety of situations and generate a fair comparison. As a demonstration, we implement the offline learning challenge in CityLearn and study the impact of different levels of domain knowledge and complexity of RL algorithms. We show that the sequence of operations utilized in a rule based controller (RBC) used for offline training affects the performance of the RL agents when evaluated on a set of four energy flexibility metrics. Longer offline learning from an optimized RBC leads to improved performance in the long run. RL agents that learn from a simplified RBC risk poorer performance as the offline learning period increases. We also observe no impact on performance from information sharing amongst agents. We call for a more interdisciplinary effort of the research community to address the real world challenges, and unlock the potential of grid-interactive building

arXiv:2112.06771공식 코드 · Papers with Code

Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution

Recent years have witnessed the great success of multi-agent systems (MAS). Value decomposition, which decomposes joint action values into individual action values, has been an important work in MAS. However, many value decomposition methods ignore the coordination among different agents, leading to the notorious "lazy agents" problem. To enhance the coordination in MAS, this paper proposes HyperGraph CoNvolution MIX (HGCN-MIX), a method that incorporates hypergraph convolution with value decomposition. HGCN-MIX models agents as well as their relationships as a hypergraph, where agents are nodes and hyperedges among nodes indicate that the corresponding agents can coordinate to achieve larger rewards. Then, it trains a hypergraph that can capture the collaborative relationships among agents. Leveraging the learned hypergraph to consider how other agents' observations and actions affect their decisions, the agents in a MAS can better coordinate. We evaluate HGCN-MIX in the StarCraft II multi-agent challenge benchmark. The experimental results demonstrate that HGCN-MIX can train joint policies that outperform or achieve a similar level of performance as the current state-of-the-art techniques. We also observe that HGCN-MIX has an even more significant improvement of performance in the scenarios with a large amount of agents. Besides, we conduct additional analysis to emphasize that when the hypergraph learns more relationships, HGCN-MIX can train stronger joint policies.

arXiv:2112.06185

Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Reward

Discovering hazardous scenarios is crucial in testing and further improving driving policies. However, conducting efficient driving policy testing faces two key challenges. On the one hand, the probability of naturally encountering hazardous scenarios is low when testing a well-trained autonomous driving strategy. Thus, discovering these scenarios by purely real-world road testing is extremely costly. On the other hand, a proper determination of accident responsibility is necessary for this task. Collecting scenarios with wrong-attributed responsibilities will lead to an overly conservative autonomous driving strategy. To be more specific, we aim to discover hazardous scenarios that are autonomous-vehicle responsible (AV-responsible), i.e., the vulnerabilities of the under-test driving policy. To this end, this work proposes a Safety Test framework by finding Av-Responsible Scenarios (STARS) based on multi-agent reinforcement learning. STARS guides other traffic participants to produce Av-Responsible Scenarios and make the under-test driving policy misbehave via introducing Hazard Arbitration Reward (HAR). HAR enables our framework to discover diverse, complex, and AV-responsible hazardous scenarios. Experimental results against four different driving policies in three environments demonstrate that STARS can effectively discover AV-responsible hazardous scenarios. These scenarios indeed correspond to the vulnerabilities of the under-test driving policies, thus are meaningful for their further improvements.

arXiv:2112.03547공식 코드 · Papers with Code

Self-Organized Polynomial-Time Coordination Graphs

Coordination graph is a promising approach to model agent collaboration in multi-agent reinforcement learning. It conducts a graph-based value factorization and induces explicit coordination among agents to complete complicated tasks. However, one critical challenge in this paradigm is the complexity of greedy action selection with respect to the factorized values. It refers to the decentralized constraint optimization problem (DCOP), which and whose constant-ratio approximation are NP-hard problems. To bypass this systematic hardness, this paper proposes a novel method, named Self-Organized Polynomial-time Coordination Graphs (SOP-CG), which uses structured graph classes to guarantee the accuracy and the computational efficiency of collaborated action selection. SOP-CG employs dynamic graph topology to ensure sufficient value function expressiveness. The graph selection is unified into an end-to-end learning paradigm. In experiments, we show that our approach learns succinct and well-adapted graph topologies, induces effective coordination, and improves performance across a variety of cooperative multi-agent tasks.

arXiv:2112.02845공식 코드 · Papers with Code

Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks

Offline reinforcement learning leverages previously-collected offline datasets to learn optimal policies with no necessity to access the real environment. Such a paradigm is also desirable for multi-agent reinforcement learning (MARL) tasks, given the increased interactions among agents and with the enviroment. Yet, in MARL, the paradigm of offline pre-training with online fine-tuning has not been studied, nor datasets or benchmarks for offline MARL research are available. In this paper, we facilitate the research by providing large-scale datasets, and use them to examine the usage of the Decision Transformer in the context of MARL. We investigate the generalisation of MARL offline pre-training in the following three aspects: 1) between single agents and multiple agents, 2) from offline pretraining to the online fine-tuning, and 3) to that of multiple downstream tasks with few-shot and zero-shot capabilities. We start by introducing the first offline MARL dataset with diverse quality levels based on the StarCraftII environment, and then propose the novel architecture of multi-agent decision transformer (MADT) for effective offline learning. MADT leverages transformer's modelling ability of sequence modelling and integrates it seamlessly with both offline and online MARL tasks. A crucial benefit of MADT is that it learns generalisable policies that can transfer between different types of agents under different task scenarios. On StarCraft II offline dataset, MADT outperforms the state-of-the-art offline RL baselines. When applied to online tasks, the pre-trained MADT significantly improves sample efficiency, and enjoys strong performance both few-short and zero-shot cases. To our best knowledge, this is the first work that studies and demonstrates the effectiveness of offline pre-trained models in terms of sample efficiency and generalisability enhancements in MARL.

arXiv:2112.02813공식 코드 · Papers with Code

MDPGT: Momentum-based Decentralized Policy Gradient Tracking

We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches over iterations. Specifically, we propose a momentum-based decentralized policy gradient tracking (MDPGT) where a new momentum-based variance reduction technique is used to approximate the local policy gradient surrogate with importance sampling, and an intermediate parameter is adopted to track two consecutive policy gradient surrogates. Moreover, MDPGT provably achieves the best available sample complexity of $\mathcal{O}(N^{-1}\epsilon^{-3})$ for converging to an $\epsilon$-stationary point of the global average of $N$ local performance functions (possibly nonconcave). This outperforms the state-of-the-art sample complexity in decentralized model-free reinforcement learning, and when initialized with a single trajectory, the sample complexity matches those obtained by the existing decentralized policy gradient methods. We further validate the theoretical claim for the Gaussian policy function. When the required error tolerance $\epsilon$ is small enough, MDPGT leads to a linear speed up, which has been previously established in decentralized stochastic optimization, but not for reinforcement learning. Lastly, we provide empirical results on a multi-agent reinforcement learning benchmark environment to support our theoretical findings.

arXiv:2112.00940

Reward-Free Attacks in Multi-Agent Reinforcement Learning

We investigate how effective an attacker can be when it only learns from its victim's actions, without access to the victim's reward. In this work, we are motivated by the scenario where the attacker wants to behave strategically when the victim's motivations are unknown. We argue that one heuristic approach an attacker can use is to maximize the entropy of the victim's policy. The policy is generally not obfuscated, which implies it may be extracted simply by passively observing the victim. We provide such a strategy in the form of a reward-free exploration algorithm that maximizes the attacker's entropy during the exploration phase, and then maximizes the victim's empirical entropy during the planning phase. In our experiments, the victim agents are subverted through policy entropy maximization, implying an attacker might not need access to the victim's reward to succeed. Hence, reward-free attacks, which are based only on observing behavior, show the feasibility of an attacker to act strategically without knowledge of the victim's motives even if the victim's reward information is protected.

arXiv:2111.15611

The Power of Communication in a Distributed Multi-Agent System

Single-Agent (SA) Reinforcement Learning systems have shown outstanding re-sults on non-stationary problems. However, Multi-Agent Reinforcement Learning(MARL) can surpass SA systems generally and when scaling. Furthermore, MAsystems can be super-powered by collaboration, which can happen through ob-serving others, or a communication system used to share information betweencollaborators. Here, we developed a distributed MA learning mechanism withthe ability to communicate based on decentralised partially observable Markovdecision processes (Dec-POMDPs) and Graph Neural Networks (GNNs). Minimis-ing the time and energy consumed by training Machine Learning models whileimproving performance can be achieved by collaborative MA mechanisms. Wedemonstrate this in a real-world scenario, an offshore wind farm, including a set ofdistributed wind turbines, where the objective is to maximise collective efficiency.Compared to a SA system, MA collaboration has shown significantly reducedtraining time and higher cumulative rewards in unseen and scaled scenarios.

arXiv:2111.14598

Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning

Safety is the primary concern when it comes to air traffic. In-flight safety between Unmanned Aircraft Vehicles (UAVs) is ensured through pairwise separation minima, utilizing conflict detection and resolution methods. Existing methods mainly deal with pairwise conflicts, however due to an expected increase in traffic density, encounters with more than two UAVs are likely to happen. In this paper, we model multi-UAV conflict resolution as a multi-agent reinforcement learning problem. We implement an algorithm based on graph neural networks where cooperative agents can communicate to jointly generate resolution maneuvers. The model is evaluated in scenarios with 3 and 4 present agents. Results show that agents are able to successfully solve the multi-UAV conflicts through a cooperative strategy.

arXiv:2111.14177

Evaluating Generalization and Transfer Capacity of Multi-Agent Reinforcement Learning Across Variable Number of Agents

Multi-agent Reinforcement Learning (MARL) problems often require cooperation among agents in order to solve a task. Centralization and decentralization are two approaches used for cooperation in MARL. While fully decentralized methods are prone to converge to suboptimal solutions due to partial observability and nonstationarity, the methods involving centralization suffer from scalability limitations and lazy agent problem. Centralized training decentralized execution paradigm brings out the best of these two approaches; however, centralized training still has an upper limit of scalability not only for acquired coordination performance but also for model size and training time. In this work, we adopt the centralized training with decentralized execution paradigm and investigate the generalization and transfer capacity of the trained models across variable number of agents. This capacity is assessed by training variable number of agents in a specific MARL problem and then performing greedy evaluations with variable number of agents for each training configuration. Thus, we analyze the evaluation performance for each combination of agent count for training versus evaluation. We perform experimental evaluations on predator prey and traffic junction environments and demonstrate that it is possible to obtain similar or higher evaluation performance by training with less agents. We conclude that optimal number of agents to perform training may differ from the target number of agents and argue that transfer across large number of agents can be a more efficient solution to scaling up than directly increasing number of agents during training.

arXiv:2111.12961

Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learning

This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL), where agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns. Due to the non-concave performance function of policy gradient, the existing distributed stochastic optimization methods for convex problems cannot be directly used for policy gradient in MARL. This paper proposes a distributed policy gradient with variance reduction and gradient tracking to address the high variances of policy gradient, and utilizes importance weight to solve the {distribution shift} problem in the sampling process. We then provide an upper bound on the mean-squared stationary gap, which depends on the number of iterations, the mini-batch size, the epoch size, the problem parameters, and the network topology. We further establish the sample and communication complexity to obtain an $\epsilon$-approximate stationary point. Numerical experiments are performed to validate the effectiveness of the proposed algorithm.

arXiv:2111.12197

Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS

Cyber attacks are increasing in volume, frequency, and complexity. In response, the security community is looking toward fully automating cyber defense systems using machine learning. However, so far the resultant effects on the coevolutionary dynamics of attackers and defenders have not been examined. In this whitepaper, we hypothesise that increased automation on both sides will accelerate the coevolutionary cycle, thus begging the question of whether there are any resultant fixed points, and how they are characterised. Working within the threat model of Locked Shields, Europe's largest cyberdefense exercise, we study blackbox adversarial attacks on network classifiers. Given already existing attack capabilities, we question the utility of optimal evasion attack frameworks based on minimal evasion distances. Instead, we suggest a novel reinforcement learning setting that can be used to efficiently generate arbitrary adversarial perturbations. We then argue that attacker-defender fixed points are themselves general-sum games with complex phase transitions, and introduce a temporally extended multi-agent reinforcement learning framework in which the resultant dynamics can be studied. We hypothesise that one plausible fixed point of AI-NIDS may be a scenario where the defense strategy relies heavily on whitelisted feature flow subspaces. Finally, we demonstrate that a continual learning approach is required to study attacker-defender dynamics in temporally extended general-sum games.

arXiv:2111.11188

Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification

Conservatism has led to significant progress in offline reinforcement learning (RL) where an agent learns from pre-collected datasets. However, as many real-world scenarios involve interaction among multiple agents, it is important to resolve offline RL in the multi-agent setting. Given the recent success of transferring online RL algorithms to the multi-agent setting, one may expect that offline RL algorithms will also transfer to multi-agent settings directly. Surprisingly, we empirically observe that conservative offline RL algorithms do not work well in the multi-agent setting -- the performance degrades significantly with an increasing number of agents. Towards mitigating the degradation, we identify a key issue that non-concavity of the value function makes the policy gradient improvements prone to local optima. Multiple agents exacerbate the problem severely, since the suboptimal policy by any agent can lead to uncoordinated global failure. Following this intuition, we propose a simple yet effective method, Offline Multi-Agent RL with Actor Rectification (OMAR), which combines the first-order policy gradients and zeroth-order optimization methods to better optimize the conservative value functions over the actor parameters. Despite the simplicity, OMAR achieves state-of-the-art results in a variety of multi-agent control tasks.

arXiv:2111.11229공식 코드 · Papers with Code

Off-Policy Correction For Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) provides a framework for problems involving multiple interacting agents. Despite apparent similarity to the single-agent case, multi-agent problems are often harder to train and analyze theoretically. In this work, we propose MA-Trace, a new on-policy actor-critic algorithm, which extends V-Trace to the MARL setting. The key advantage of our algorithm is its high scalability in a multi-worker setting. To this end, MA-Trace utilizes importance sampling as an off-policy correction method, which allows distributing the computations with no impact on the quality of training. Furthermore, our algorithm is theoretically grounded - we prove a fixed-point theorem that guarantees convergence. We evaluate the algorithm extensively on the StarCraft Multi-Agent Challenge, a standard benchmark for multi-agent algorithms. MA-Trace achieves high performance on all its tasks and exceeds state-of-the-art results on some of them.

arXiv:2111.11129공식 코드 · Papers with Code

Multi-lingual agents through multi-headed neural networks

This paper considers cooperative Multi-Agent Reinforcement Learning, focusing on emergent communication in settings where multiple pairs of independent learners interact at varying frequencies. In this context, multiple distinct and incompatible languages can emerge. When an agent encounters a speaker of an alternative language, there is a requirement for a period of adaptation before they can efficiently converse. This adaptation results in the emergence of a new language and the forgetting of the previous language. In principle, this is an example of the Catastrophic Forgetting problem which can be mitigated by enabling the agents to learn and maintain multiple languages. We take inspiration from the Continual Learning literature and equip our agents with multi-headed neural networks which enable our agents to be multi-lingual. Our method is empirically validated within a referential MNIST based communication game and is shown to be able to maintain multiple languages where existing approaches cannot.

arXiv:2111.11032

Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration

Efficient exploration in deep cooperative multi-agent reinforcement learning (MARL) still remains challenging in complex coordination problems. In this paper, we introduce a novel Episodic Multi-agent reinforcement learning with Curiosity-driven exploration, called EMC. We leverage an insight of popular factorized MARL algorithms that the "induced" individual Q-values, i.e., the individual utility functions used for local execution, are the embeddings of local action-observation histories, and can capture the interaction between agents due to reward backpropagation during centralized training. Therefore, we use prediction errors of individual Q-values as intrinsic rewards for coordinated exploration and utilize episodic memory to exploit explored informative experience to boost policy training. As the dynamics of an agent's individual Q-value function captures the novelty of states and the influence from other agents, our intrinsic reward can induce coordinated exploration to new or promising states. We illustrate the advantages of our method by didactic examples, and demonstrate its significant outperformance over state-of-the-art MARL baselines on challenging tasks in the StarCraft II micromanagement benchmark.

arXiv:2111.10898

Renewable energy integration and microgrid energy trading using multi-agent deep reinforcement learning

In this paper, multi-agent reinforcement learning is used to control a hybrid energy storage system working collaboratively to reduce the energy costs of a microgrid through maximising the value of renewable energy and trading. The agents must learn to control three different types of energy storage system suited for short, medium, and long-term storage under fluctuating demand, dynamic wholesale energy prices, and unpredictable renewable energy generation. Two case studies are considered: the first looking at how the energy storage systems can better integrate renewable energy generation under dynamic pricing, and the second with how those same agents can be used alongside an aggregator agent to sell energy to self-interested external microgrids looking to reduce their own energy bills. This work found that the centralised learning with decentralised execution of the multi-agent deep deterministic policy gradient and its state-of-the-art variants allowed the multi-agent methods to perform significantly better than the control from a single global agent. It was also found that using separate reward functions in the multi-agent approach performed much better than using a single control agent. Being able to trade with the other microgrids, rather than just selling back to the utility grid, also was found to greatly increase the grid's savings.

arXiv:2111.10627

Calculus of Consent via MARL: Legitimating the Collaborative Governance Supplying Public Goods

Public policies that supply public goods, especially those involve collaboration by limiting individual liberty, always give rise to controversies over governance legitimacy. Multi-Agent Reinforcement Learning (MARL) methods are appropriate for supporting the legitimacy of the public policies that supply public goods at the cost of individual interests. Among these policies, the inter-regional collaborative pandemic control is a prominent example, which has become much more important for an increasingly inter-connected world facing a global pandemic like COVID-19. Different patterns of collaborative strategies have been observed among different systems of regions, yet it lacks an analytical process to reason for the legitimacy of those strategies. In this paper, we use the inter-regional collaboration for pandemic control as an example to demonstrate the necessity of MARL in reasoning, and thereby legitimizing policies enforcing such inter-regional collaboration. Experimental results in an exemplary environment show that our MARL approach is able to demonstrate the effectiveness and necessity of restrictions on individual liberty for collaborative supply of public goods. Different optimal policies are learned by our MARL agents under different collaboration levels, which change in an interpretable pattern of collaboration that helps to balance the losses suffered by regions of different types, and consequently promotes the overall welfare. Meanwhile, policies learned with higher collaboration levels yield higher global rewards, which illustrates the benefit of, and thus provides a novel justification for the legitimacy of, promoting inter-regional collaboration. Therefore, our method shows the capability of MARL in computationally modeling and supporting the theory of calculus of consent, developed by Nobel Prize winner J. M. Buchanan.

arXiv:2111.09410

EdgeML: Towards Network-Accelerated Federated Learning over Wireless Edge

Federated learning (FL) is a distributed machine learning technology for next-generation AI systems that allows a number of workers, i.e., edge devices, collaboratively learn a shared global model while keeping their data locally to prevent privacy leakage. Enabling FL over wireless multi-hop networks can democratize AI and make it accessible in a cost-effective manner. However, the noisy bandwidth-limited multi-hop wireless connections can lead to delayed and nomadic model updates, which significantly slows down the FL convergence speed. To address such challenges, this paper aims to accelerate FL convergence over wireless edge by optimizing the multi-hop federated networking performance. In particular, the FL convergence optimization problem is formulated as a Markov decision process (MDP). To solve such MDP, multi-agent reinforcement learning (MA-RL) algorithms along with domain-specific action space refining schemes are developed, which online learn the delay-minimum forwarding paths to minimize the model exchange latency between the edge devices (i.e., workers) and the remote server. To validate the proposed solutions, FedEdge is developed and implemented, which is the first experimental framework in the literature for FL over multi-hop wireless edge computing networks. FedEdge allows us to fast prototype, deploy, and evaluate novel FL algorithms along with RL-based system optimization methods in real wireless devices. Moreover, a physical experimental testbed is implemented by customizing the widely adopted Linux wireless routers and ML computing nodes.Finally, our experimentation results on the testbed show that the proposed network-accelerated FL system can practically and significantly improve FL convergence speed, compared to the FL system empowered by the production-grade commercially available wireless networking protocol, BATMAN-Adv.

arXiv:2111.09152

Improved cooperation by balancing exploration and exploitation in intertemporal social dilemma tasks

When an individual's behavior has rational characteristics, this may lead to irrational collective actions for the group. A wide range of organisms from animals to humans often evolve the social attribute of cooperation to meet this challenge. Therefore, cooperation among individuals is of great significance for allowing social organisms to adapt to changes in the natural environment. Based on multi-agent reinforcement learning, we propose a new learning strategy for achieving coordination by incorporating a learning rate that can balance exploration and exploitation. We demonstrate that agents that use the simple strategy improve a relatively collective return in a decision task called the intertemporal social dilemma, where the conflict between the individual and the group is particularly sharp. We also explore the effects of the diversity of learning rates on the population of reinforcement learning agents and show that agents trained in heterogeneous populations develop particularly coordinated policies relative to those trained in homogeneous populations.