We consider communication in a fully cooperative multi-agent system, where the agents have partial observation of the environment and must act jointly to maximize the overall reward. We have a discrete-time queueing network where agents route packets to queues based only on the partial information of the current queue lengths. The queues have limited buffer capacity, so packet drops happen when they are sent to a full queue. In this work, we implemented a communication channel for the agents to share their information in order to reduce the packet drop rate. For efficient information sharing we use an attention-based communication model, called ATVC, to select informative messages from other agents. The agents then infer the state of queues using a combination of the variational auto-encoder, VAE, and product-of-experts, PoE, model. Ultimately, the agents learn what they need to communicate and with whom, instead of communicating all the time with everyone. We also show empirically that ATVC is able to infer the true state of the queues and leads to a policy which outperforms existing baselines.

Recently, intent-based management has received good attention in telecom networks owing to stringent performance requirements for many of the use cases. Several approaches in the literature employ traditional closed-loop driven methods to fulfill the intents on the KPIs. However, these methods consider every closed-loop independent of each other which degrades the combined performance. Also, such existing methods are not easily scalable. Multi-agent reinforcement learning (MARL) techniques have shown significant promise in many areas in which traditional closed-loop control falls short, typically for complex coordination and conflict management among loops. In this work, we propose a method based on MARL to achieve intent-based management without the need for knowing a model of the underlying system. Moreover, when there are conflicting intents, the MARL agents can implicitly incentivize the loops to cooperate and promote trade-offs, without human interaction, by prioritizing the important KPIs. Experiments have been performed on a network emulator for optimizing KPIs of three services. Results obtained demonstrate that the proposed system performs quite well and is able to fulfill all existing intents when there are enough resources or prioritize the KPIs when resources are scarce.

Simulation is the key to scaling up validation and verification for robotic systems such as autonomous vehicles. Despite advances in high-fidelity physics and sensor simulation, a critical gap remains in simulating realistic behaviors of road users. This is because, unlike simulating physics and graphics, devising first principle models for human-like behaviors is generally infeasible. In this work, we take a data-driven approach and propose a method that can learn to generate traffic behaviors from real-world driving logs. The method achieves high sample efficiency and behavior diversity by exploiting the bi-level hierarchy of driving behaviors by decoupling the traffic simulation problem into high-level intent inference and low-level driving behavior imitation. The method also incorporates a planning module to obtain stable long-horizon behaviors. We empirically validate our method, named Bi-level Imitation for Traffic Simulation (BITS), with scenarios from two large-scale driving datasets and show that BITS achieves balanced traffic simulation performance in realism, diversity, and long-horizon stability. We also explore ways to evaluate behavior realism and introduce a suite of evaluation metrics for traffic simulation. Finally, as part of our core contributions, we develop and open source a software tool that unifies data formats across different driving datasets and converts scenes from existing datasets into interactive simulation environments. For additional information and videos, see https://sites.google.com/view/nvr-bits2022/home

Cooperative task execution, a hallmark of eusociality, is enabled by local interactions between the agents and the environment through a dynamically evolving communication signal. Inspired by the collective behavior of social insects whose dynamics is modulated by interactions with the environment, we show that a robot collective can successfully nucleate a construction site via a trapping instability and cooperatively build organized structures. The same robot collective can also perform de-construction with a simple change in the behavioral parameter. These behaviors belong to a two-dimensional phase space of cooperative behaviors defined by agent-agent interaction (cooperation) along one axis and the agent-environment interaction (collection and deposition) on the other. Our behavior-based approach to robot design combined with a principled derivation of local rules enables the collective to solve tasks with robustness to a dynamically changing environment and a wealth of complex behaviors. The solution of complex problems on scales much This naturally raises two questions: (i) how do we design larger than the size of an individual, in both natural [1-8] a set of microscopic behavioral rules at the level of an individual and artificial systems [9-12], often requires the cooperative agent that leads to the emergence of robust and effort of a collective. An example is the collective flexible task completion? One difficulty is derive a principled approach for the synthesis of a broader that the participating agents in a collective must interact class of cooperative behaviors: collective architecture.

For massive large-scale tasks, a multi-robot system (MRS) can effectively improve efficiency by utilizing each robot's different capabilities, mobility, and functionality. In this paper, we focus on the multi-robot coverage path planning (mCPP) problem in large-scale planar areas with random dynamic interferers in the environment, where the robots have limited resources. We introduce a worker-station MRS consisting of multiple workers with limited resources for actual work, and one station with enough resources for resource replenishment. We aim to solve the mCPP problem for the worker-station MRS by formulating it as a fully cooperative multi-agent reinforcement learning problem. Then we propose an end-to-end decentralized online planning method, which simultaneously solves coverage planning for workers and rendezvous planning for station. Our method manages to reduce the influence of random dynamic interferers on planning, while the robots can avoid collisions with them. We conduct simulation and real robot experiments, and the comparison results show that our method has competitive performance in solving the mCPP problem for worker-station MRS in metric of task finish time.

Reinforcement Learning has recently surfaced as a very powerful tool to solve complex problems in the domain of board games, wherein an agent is generally required to learn complex strategies and moves based on its own experiences and rewards received. While RL has outperformed existing state-of-the-art methods used for playing simple video games and popular board games, it is yet to demonstrate its capability on ancient games. Here, we solve one such problem, where we train our agents using different methods namely Monte Carlo, Qlearning and Expected Sarsa to learn optimal policy to play the strategic Royal Game of Ur. The state space for our game is complex and large, but our agents show promising results at playing the game and learning important strategic moves. Although it is hard to conclude that when trained with limited resources which algorithm performs better overall, but Expected Sarsa shows promising results when it comes to fastest learning.

The value alignment problem is concerned with the design of systems that provably abide by our human values. One approach to this challenge is through the leverage of prescriptive norms that, if carefully designed, are able to steer a multiagent system away from harmful outcomes and towards more beneficial ones. In this work, we first present a general methodology for the automated synthesis of value aligned normative systems, based on a consequentialist view of values. In the second part, we provide analytical tools to examine such value aligned normative systems, namely the Shapley value of individual norms and the compatibility of several values under a fixed set of norms. We illustrate all of our contributions with a running example of a society of agents where taxes are collected and redistributed according to a set of parametrised norms.

Recent years have seen significant advances in explainable AI as the need to understand deep learning models has gained importance with the increased emphasis on trust and ethics in AI. Comprehensible models for sequential decision tasks are a particular challenge as they require understanding not only individual predictions but a series of predictions that interact with environmental dynamics. We present a framework for learning comprehensible models of sequential decision tasks in which agent strategies are characterized using temporal logic formulas. Given a set of agent traces, we first cluster the traces using a novel embedding method that captures frequent action patterns. We then search for logical formulas that explain the agent strategies in the different clusters. We evaluate our framework on combat scenarios in StarCraft II (SC2), using traces from a handcrafted expert policy and a trained reinforcement learning agent. We implemented a feature extractor for SC2 environments that extracts traces as sequences of high-level features describing both the state of the environment and the agent's local behavior from agent replays. We further designed a visualization tool depicting the movement of units in the environment that helps understand how different task conditions lead to distinct agent behavior patterns in each trace cluster. Experimental results show that our framework is capable of separating agent traces into distinct groups of behaviors for which our approach to strategy inference produces consistent, meaningful, and easily understood strategy descriptions.

In cooperative multi-agent reinforcement learning (MARL), due to its on-policy nature, policy gradient (PG) methods are typically believed to be less sample efficient than value decomposition (VD) methods, which are off-policy. However, some recent empirical studies demonstrate that with proper input representation and hyper-parameter tuning, multi-agent PG can achieve surprisingly strong performance compared to off-policy VD methods. Why could PG methods work so well? In this post, we will present concrete analysis to show that in certain scenarios, e.g., environments with a highly multi-modal reward landscape, VD can be problematic and lead to undesired outcomes. In addition, PG methods with auto-regressive (AR) policies can learn multi-modal policies.

The StarCraft II Multi-Agent Challenge (SMAC) was created to be a challenging benchmark problem for cooperative multi-agent reinforcement learning (MARL). SMAC focuses exclusively on the problem of StarCraft micromanagement and assumes that each unit is controlled individually by a learning agent that acts independently and only possesses local information; centralized training is assumed to occur with decentralized execution (CTDE). To perform well in SMAC, MARL algorithms must handle the dual problems of multi-agent credit assignment and joint action evaluation. This paper introduces a new architecture TransMix, a transformer-based joint action-value mixing network which we show to be efficient and scalable as compared to the other state-of-the-art cooperative MARL solutions. TransMix leverages the ability of transformers to learn a richer mixing function for combining the agents' individual value functions. It achieves comparable performance to previous work on easy SMAC scenarios and outperforms other techniques on hard scenarios, as well as scenarios that are corrupted with Gaussian noise to simulate fog of war.