New Zealand


Recent studies in multi-agent communicative reinforcement learning (MACRL) have demonstrated that multi-agent coordination can be greatly improved by allowing communication between agents. Meanwhile, adversarial machine learning (ML) have shown that ML models are vulnerable to attacks. Despite the increasing concern about the robustness of ML algorithms, how to achieve robust communication in multi-agent reinforcement learning has been largely neglected. In this paper, we systematically explore the problem of adversarial communication in MACRL. Our main contributions are threefold. First, we propose an effective method to perform attacks in MACRL, by learning a model to generate optimal malicious messages. Second, we develop a defence method based on message reconstruction, to maintain multi-agent coordination under message attacks. Third, we formulate the adversarial communication problem as a two-player zero-sum game and propose a game-theoretical method R-MACRL to improve the worst-case defending performance. Empirical results demonstrate that many state-of-the-art MACRL methods are vulnerable to message attacks, and our method can significantly improve their robustness.

AAMAS 2022

Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning

adversarial reinforcement learning

robust reinforcement learning

multi-agent reinforcement learning

Naval Information Warfare Center Pacific is partnering with AFCEA San Diego chapter to host the workshop.

The NAML workshop is an opportunity for researchers from Navy research and development centers and our partner organizations to exchange technical ideas and to come together as a team.

The goals of NAML are:

* To spread awareness of current machine learning research relevant to Naval applications

* To connect machine learning researchers with experts in military requirements

* To build and strengthen collaborations within the defense research community

**Watch this video to hear about the AFCEA purpose.**

<iframe width=1280 height=706 frameborder="0" scrolling="no" src="https://screencast-o-matic.com/player/creleVVcvRh?v=6&ff=1&title=0&controls=1" allowfullscreen="true"></iframe>

NAML 2021

technical paper

AAMAS (International Conference on Autonomous Agents and Multiagent Systems) is the largest and most influential conference in the area of agents and multiagent systems. The aim of the conference is to bring together researchers and practitioners in all areas of agent technology and to provide a single, high-profile, internationally renowned forum for research in the theory and practice of autonomous agents and multiagent systems. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).

The AAMAS conference series was initiated in 2002 in Bologna, Italy as a joint event comprising the 6th International Conference on Autonomous Agents (AA), the 5th International Conference on Multiagent Systems (ICMAS), and the 9th International Workshop on Agent Theories, Architectures, and Languages (ATAL).

Subsequent AAMAS conferences have been held in Melbourne, Australia (July 2003), New York City, NY, USA (July 2004), Utrecht, The Netherlands (July 2005), Hakodate, Japan (May 2006), Honolulu, Hawaii, USA (May 2007), Estoril, Portugal (May 2008), Budapest, Hungary (May 2009), Toronto, Canada (May 2010), Taipei, Taiwan (May 2011), Valencia, Spain (June 2012), Minnesota, USA (May 2013), Paris, France (May 2014), Istanbul, Turkey (May 2015), Singapore (May 2016), São Paulo (2017) and Stockholm, Sweden (2018), Montreal (May 2019), Auckland (May 2020, Virtual), London (May 2021, Virtual).
<br>
<br>



A ticket is required to attend this event, please register using the link below:

https://aamas2022-conference.auckland.ac.nz/attending/registration/

Registration Is Required

AAMAS (International Conference on Autonomous Agents and Multiagent Systems) is the largest and most influential conference in the area of agents and multiagent systems. The aim of the conference is to bring together researchers and practitioners in all areas of agent technology and to provide a single, high-profile, internationally renowned forum for research in the theory and practice of autonomous agents and multiagent systems. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).


Traditionally, Reinforcement Learning (RL) aims at deciding how to act optimally for an artificial agent. We argue that deciding when to act is equally important. As humans, we drift from default, instinctive or memorized behaviors to focused, thought-out behaviors when required by the situation. To enhance RL agents with this aptitude, we propose to augment the standard Markov Decision Process and make a new mode of action available: the lazy mode, which defers decision-making to a given default policy. In addition, we penalize non-lazy actions in order to enforce minimal effort and have agents focus on critical decisions only. We name the resulting formalism lazy-MDPs. We study the theoretical properties of lazy-MDPs, expressing value functions and characterizing greediness and optimal solutions. Then we empirically demonstrate that policies learned in lazy-MDPs are generally more interpretable and highlight the states where it is important for the agent to act. When the default policy is uniformly random, we observe that agents are still able to approximate or even to surpass classic DQN agents on some Atari games while only taking control at a fewer subset of the states.

Lazy-MDPs: Towards Interpretable RL by Learning When to Act


Imitation learning (IL) is a popular paradigm for training policies in robotic systems when specifying the reward function is difficult. However, despite the success of IL algorithms, they impose the somewhat unrealistic requirement that the expert demonstrations must come from the same domain in which a new imitator policy is to be learned. We consider a practical setting, where (i) state-only expert demonstrations from the real (deployment) environment are given to the learner, (ii) the imitation learner policy is trained in a simulation (training) environment whose transition dynamics is slightly different from the real environment, and (iii) the learner does not have any access to the real environment during the training phase beyond the batch of demonstrations given. Most of the current IL methods, such as generative adversarial imitation learning and its state-only variants, fail to imitate the optimal expert behavior under the above setting. By leveraging insights from the Robust reinforcement learning (RL) literature and building on recent adversarial imitation approaches, we propose a robust IL algorithm to learn policies that can effectively transfer to the real environment without fine-tuning. Furthermore, we empirically demonstrate on continuous-control benchmarks that our method outperforms the state-of-the-art state-only IL method in terms of the zero-shot transfer performance in the real environment and robust performance under different testing conditions.

Robust Learning from Observation with Model Misspecification


In this work, we give an operational semantics for speech acts that BDI agents can use to communicate enthymemes. The approach uses argumentation schemes as common organisational knowledge to guide the construction of enthymemes by the proponents of arguments. Such schemes are also used to guide the reconstruction of the intended argument by the recipients of such enthymemes.

Towards an Enthymeme-Based Communication Framework


We consider average-based and min-based altruistic hedonic games and study the problem of verifying popular and strictly popular coalition structures. While strict popularity verification has been shown to be coNP-complete in min-based altruistic hedonic games, this problem has been open for equal-treatment and altruistic-treatment average-based altruistic hedonic games. We solve these two open cases of strict popularity verification and then provide the first complexity results for popularity verification in (both average- and min-based) altruistic hedonic games, where we cover all three degrees of altruism.

Popularity and Strict Popularity in Altruistic Hedonic Games and Minimum-Based Altruistic Hedonic Games

**Read paper on the following link:**

https://ifaamas.org/Proceedings/aamas2022/pdfs/p1551.pdf

**Abstract:**



Contrastive Explanations for Argumentation-Based Conclusions


In many practical applications, we often need to form a team of agents to solve a task, since no agent alone has the full set of required competences or the power to complete the task on time. Here, we address the problem of distributing individuals in teams, with each team being in charge of a specific task. In particular, we formalise the problem and propose a heuristic approach to solve it.

An anytime heuristic algorithm for allocating many teams to many tasks


Call centers, in which human operators attend clients using textual chat, are very common in modern e-commerce. Training enough skilled operators who are able to provide good service is a challenge. We propose a methodology for the development of an assisting agent that provides online advice to operators while they attend clients. The agent is easy-to-build and can be introduced to new domains without major effort in design, training and organizing structured knowledge of the professional discipline. We demonstrate the applicability of the system in an experiment that realizes its full life-cycle on a specific domain, and analyze its capabilities.

Advising Agent for Service-Providing Live-Chat Operators


In this paper we put forward a novel extension of the classic Max-sum algorithm to the framework of Continuous Distributed Constrained Optimization Problems (Continuous DCOPs), in which we model the exchanged messages by means of a popular geometric algorithm, Quadtrees. As such, the discretization process is dynamic and embedded in the internal Max-sum operations (addition and marginal maximization). We apply our Max-sum with Quadtrees approach to Lane-Free Autonomous Driving in a highway populated with vehicles. Our experimental evaluation verifies the efficiency of our approach in this challenging dynamic coordination domain, demonstrating its superior performance with respect to the standard Max-sum algorithm.

Max-sum with Quadtrees for Continuous DCOPs with Application to Lane-Free Autonomous Driving

For autonomous agents to successfully perform in open hybrid scenarios (with people and agents), they need to adapt to different social contexts. 
Simultaneously, the people involved must understand the observed changes in the agents, particularly to identify the social motivations for such behavior.
In this paper, we report an experimental study conducted to assess if an agent's behavioral changes (gait), are perceived as more socially motivated than its appearance adaptations (color). Furthermore, we explore if other agents' presence and behavior affect the attribution of motivations.
Our findings suggest that external observers identify agents' appearance adaptations as more socially and spatially motivated than behavioral changes. Furthermore, the agents' awareness is rated higher when the agents adjust their physical characteristics compared to behavioral adaptations.

Behavior vs Appearance: what type of adaptations are more socially motivated?


Round-robin tournaments are, besides single-elimination tournaments, by far the most prominent and widely used tournament format in sports and other competitions. We study the average-case complexity of two problems related to the prediction of roundrobin tournaments, namely first the problem of calculating the championship probability of a team and second the well-known sports elimination problem where one has to decide whether a team still has the possibility to become champion. We show that, under certain assumptions, these problems are solvable in expected polynomial time for a distribution which, for the algorithm used, seems to dominate the distribution of real instances in terms of complexity, despite their computational worst-case hardness.

Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning

Downloads

Next from AAMAS 2022

Lazy-MDPs: Towards Interpretable RL by Learning When to Act

Similar lecture

Cooperative Multi-Agent Reinforcement Learning for Cyber Defense

Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAMAS 2022

Lazy-MDPs: Towards Interpretable RL by Learning When to Act

Similar lecture

Cooperative Multi-Agent Reinforcement Learning for Cyber Defense

Downloads