Millimeter wave (mmWave) has been recognized as one of key technologies for 5G and beyond networks due to its potential to enhance channel bandwidth and network capacity. The use of mmWave for various applications including vehicular communications has been extensively discussed. However, applying mmWave to vehicular communications faces challenges of high mobility nodes and narrow coverage along the mmWave beams. Due to high mobility in dense networks, overlapping beams can cause strong interference which leads to performance degradation. As a remedy, beam switching capability in mmWave can be utilized. Then, frequent beam switching and cell change become inevitable to manage interference, which increase computational and signalling complexity. In order to deal with the complexity in interference control, we develop a new strategy called Multi-Agent Context Learning (MACOL), which utilizes Contextual Bandit to manage interference while allocating mmWave beams to serve vehicles in the network. Our approach demonstrates that by leveraging knowledge of neighbouring beam status, the machine learning agent can identify and avoid potential interfering transmissions to other ongoing transmissions. Furthermore, we show that even under heavy traffic loads, our proposed MACOL strategy is able to maintain low interference levels at around 10%.

In this paper, we aim to utilize only offline trajectory data to train a policy for multi-objective RL. We extend the offline policy-regularized method, a widely-adopted approach for single-objective offline RL problems, into the multi-objective setting in order to achieve the above goal. However, such methods face a new challenge in offline MORL settings, namely the preference-inconsistent demonstration problem. We propose two solutions to this problem: 1) filtering out preference-inconsistent demonstrations via approximating behavior preferences, and 2) adopting regularization techniques with high policy expressiveness. Moreover, we integrate the preference-conditioned scalarized update method into policy-regularized offline RL, in order to simultaneously learn a set of policies using a single policy network, thus reducing the computational cost induced by the training of a large number of individual policies for various preferences. Finally, we introduce Regularization Weight Adaptation to dynamically determine appropriate regularization weights for arbitrary target preferences during deployment. Empirical results on various multi-objective datasets demonstrate the capability of our approach in solving offline MORL problems.

Cloud computing is an attractive technology for providing computing resources over the Internet. Task scheduling is a critical issue in cloud computing, where an efficient task scheduling method can improve overall cloud performance. Since cloud computing is a large-scale and geographically distributed environment, traditional scheduling methods that allocate resources in a centralized manner are ineffective. Besides, traditional methods are difficult to make rational decisions timely when the external environment changes. This paper proposes a decentralized BDI (belief-desire-intention) agent-based scheduling framework for cloud computing. BDI agents have advantages in modelling dynamic environments because BDI agents can update their beliefs, change desires, and trigger behaviours based on environmental changes. Besides, to avoid communication stuck caused by environmental uncertainties, the asynchronous communication mode with a notify listener is employed. The proposed framework covers both the task scheduling and rescheduling stages with the consideration of uncertain events that can interrupt task executions. Two agent-based algorithms are proposed to implement the task scheduling and rescheduling processes, and a novel recommendation mechanism is presented in the scheduling stage to reduce the impact of information synchronization delays. The proposed framework is implemented by JADEX and tested on CloudSim. The experimental results show that our framework can minimize the task makespan, balance the resource utilization in a large-scale environment, and maximize the task success rate when uncertain events occur.

Fog computing has become an attractive research topic in recent years. As an extension of the cloud, fog computing provides computing resources for Internet of Things (IoT) applications through communicative fog nodes located at the network edge. Fog nodes assist cloud services in handling real-time and mobile applications by bringing the processing capability to where the data is generated. However, the introduction of fog nodes can increase scheduling openness and uncertainty. The scheduling issues in fog computing need to consider the geography, load balancing, and network latency between IoT devices, fog nodes, as well as the parent cloud. Besides, the scheduling methods also need to deal with the occurrence of uncertain events in real-time so as to ensure service reliability. This paper proposes an agent-based framework with a decentralized structure to construct the architecture of fog computing, while three agent-based algorithms are proposed to implement the scheduling, load balance, and rescheduling processes. The proposed framework is implemented by JADE and evaluated on the iFogSim toolkit. Experimental results show that the proposed scheduling framework can adaptively schedule tasks and resources for different service requests in fog computing and can also improve the task success rate when uncertain events occur.

In this report, we explore the ability of language model agents to acquire resources, create copies of themselves, and adapt to novel challenges they encounter in the wild. We refer to this cluster of capabilities as "autonomous replication and adaptation" or ARA. We believe that systems capable of ARA could have wide-reaching and hard-to-anticipate consequences, and that measuring and forecasting ARA may be useful for informing measures around security, monitoring, and alignment. Additionally, once a system is capable of ARA, placing bounds on a system's capabilities may become significantly more difficult. We construct four simple example agents that combine language models with tools that allow them to take actions in the world. We then evaluate these agents on 12 tasks relevant to ARA. We find that these language model agents can only complete the easiest tasks from this list, although they make some progress on the more challenging tasks. Unfortunately, these evaluations are not adequate to rule out the possibility that near-future agents will be capable of ARA. In particular, we do not think that these evaluations provide good assurance that the ``next generation'' of language models (e.g. 100x effective compute scaleup on existing models) will not yield agents capable of ARA, unless intermediate evaluations are performed during pretraining. Relatedly, we expect that fine-tuning of the existing models could produce substantially more competent agents, even if the fine-tuning is not directly targeted at ARA.

Centralized Training with Decentralized Execution (CTDE) has been proven to be an effective paradigm in cooperative multi-agent reinforcement learning (MARL). One of the major challenges is credit assignment, which aims to credit agents by their contributions. While prior studies have shown great success, their methods typically fail to work in episodic reinforcement learning scenarios where global rewards are revealed only at the end of the episode. They lack the functionality to model complicated relations of the delayed global reward in the temporal dimension and suffer from inefficiencies. To tackle this, we introduce Spatial-Temporal Attention with Shapley (STAS), a novel method that learns credit assignment in both temporal and spatial dimensions. It first decomposes the global return back to each time step, then utilizes the Shapley Value to redistribute the individual payoff from the decomposed global reward. To mitigate the computational complexity of the Shapley Value, we introduce an approximation of marginal contribution and utilize Monte Carlo sampling to estimate it. We evaluate our method on an Alice & Bob example and MPE environments across different scenarios. Our results demonstrate that our method effectively assigns spatial-temporal credit, outperforming all state-of-the-art baselines.

Federated learning (FL) has become a popular tool for solving traditional Reinforcement Learning (RL) tasks. The multi-agent structure addresses the major concern of data-hungry in traditional RL, while the federated mechanism protects the data privacy of individual agents. However, the federated mechanism also exposes the system to poisoning by malicious agents that can mislead the trained policy. Despite the advantage brought by FL, the vulnerability of Federated Reinforcement Learning (FRL) has not been well-studied before. In this work, we propose a general framework to characterize FRL poisoning as an optimization problem and design a poisoning protocol that can be applied to policy-based FRL. Our framework can also be extended to FRL with actor-critic as a local RL algorithm by training a pair of private and public critics. We provably show that our method can strictly hurt the global objective. We verify our poisoning effectiveness by conducting extensive experiments targeting mainstream RL algorithms and over various RL OpenAI Gym environments covering a wide range of difficulty levels. Within these experiments, we compare clean and baseline poisoning methods against our proposed framework. The results show that the proposed framework is successful in poisoning FRL systems and reducing performance across various environments and does so more effectively than baseline methods. Our work provides new insights into the vulnerability of FL in RL training and poses new challenges for designing robust FRL algorithms

Sinhala is the native language of the Sinhalese people who make up the largest ethnic group of Sri Lanka. The language belongs to the globe-spanning language tree, Indo-European. However, due to poverty in both linguistic and economic capital, Sinhala, in the perspective of Natural Language Processing tools and research, remains a resource-poor language which has neither the economic drive its cousin English has nor the sheer push of the law of numbers a language such as Chinese has. A number of research groups from Sri Lanka have noticed this dearth and the resultant dire need for proper tools and research for Sinhala natural language processing. However, due to various reasons, these attempts seem to lack coordination and awareness of each other. The objective of this paper is to fill that gap of a comprehensive literature survey of the publicly available Sinhala natural language tools and research so that the researchers working in this field can better utilize contributions of their peers. As such, we shall be uploading this paper to arXiv and perpetually update it periodically to reflect the advances made in the field.

One of the final frontiers in the development of complex human - AI collaborative systems is the ability of AI agents to comprehend the natural language and perform tasks accordingly. However, training efficient Reinforcement Learning (RL) agents grounded in natural language has been a long-standing challenge due to the complexity and ambiguity of the language and sparsity of the rewards, among other factors. Several advances in reinforcement learning, curriculum learning, continual learning, language models have independently contributed to effective training of grounded agents in various environments. Leveraging these developments, we present a novel algorithm, Grounded Language Instruction through DEmonstration in RL (GLIDE-RL) that introduces a teacher-instructor-student curriculum learning framework for training an RL agent capable of following natural language instructions that can generalize to previously unseen language instructions. In this multi-agent framework, the teacher and the student agents learn simultaneously based on the student's current skill level. We further demonstrate the necessity for training the student agent with not just one, but multiple teacher agents. Experiments on a complex sparse reward environment validates the effectiveness of our proposed approach.

Decentralized optimization methods often entail information exchange between neighbors. Transmission failures can happen due to network congestion, hardware/software issues, communication outage, and other factors. In this paper, we investigate the random link failure problem in decentralized multi-task online convex optimization, where agents have individual decisions that are coupled with each other via pairwise constraints. Although widely used in constrained optimization, conventional saddle-point algorithms are not directly applicable here because of random packet dropping. To address this issue, we develop a robust decentralized saddle-point algorithm against random link failures with heterogeneous probabilities by replacing the missing decisions of neighbors with their latest received values. Then, by judiciously bounding the accumulated deviation stemming from this replacement, we first establish that our algorithm achieves $\mathcal{O}(\sqrt{T})$ regret and $\mathcal{O}(T^\frac{3}{4})$ constraint violations for the full information scenario, where the complete information on the local cost function is revealed to each agent at the end of each time slot. These two bounds match, in order sense, the performance bounds of algorithms with perfect communications. Further, we extend our algorithm and analysis to the two-point bandit feedback scenario, where only the values of the local cost function at two random points are disclosed to each agent sequentially. Performance bounds of the same orders as the full information case are derived. Finally, we corroborate the efficacy of the proposed algorithms and the analytical results through numerical simulations.