New Zealand


Multi-agent reinforcement learning (MARL) requires coordination by some means of interaction between agents to efficiently solve tasks. Interaction graphs allow reasoning about joint actions based on the local structure of interactions, but they disregard the potential impact of an agent’s action on its neighbors’ behaviors, which could rapidly alter in dynamic settings. In this paper, we thus present a novel perspective on opponent modeling in domains with only local interactions using (level-1) Graph Probabilistic Recursive Reasoning (GrPR2). Unlike previous work on recursive reasoning, each agent iteratively best-responds to other agents’ policies over all possible local interactions. Agents’ policies are approximated via a variational Bayes scheme for capturing their uncertainties, and we prove that an induced variant of Q-learning converges under self-play when there exists only one Nash equilibrium. In cooperative settings, we further devise a variational lower bound on the likelihood of each agent&#39;s optimality. Opposed to other models, optimizing the resulting objective prevents each agent from attaining an unrealistic modelling of others, and yields an exact tabular Q-iteration method that holds convergence guarantees. Then, we deepen the recursion to level-k via Cognitive Hierarchy GrPR2 (GrPR2-CH), which lets each level-k player best-respond to a mixture of strictly lower levels in the hierarchy. We prove that: (1) level-3 reasoning is the optimal hierarchical level, maximizing each agent&#39;s expected return; and (2) the weak spot of the classical CH models is that 0-level is uniformly distributed, as it may introduce policy bias. Finally, we propose a practical actor-critic scheme, and illustrate that GrPR2-CH outperforms strong MARL baselines in the particle environment.

AAMAS 2022

Optimizing Multi-Agent Coordination via Hierarchical Graph Probabilistic Recursive Reasoning

multi-agent reinforcement learning; multi-agent coordination; interaction graphs; cognitive hierarchy; variational inference

The AGI conference series is the only major conference series devoted wholly and specifically to the creation of AI systems possessing general intelligence at the human level and ultimately beyond. By gathering together active researchers in the field, for presentation of results and discussion of ideas, we accelerate our progress toward our common goal.

Underline hosted the two main days of AGI 2020 on Wednesday June 24th and Thursday June 25th. Both days were **live-streamed** and you can read the full program bellow. All presentations are available for a **asynchronous viewing**. All presenters are grouped into panels. You can also hear guest talks by **Ben Goertzel** (SingularityNET), **Valery Tarasov** (Semenov Institute of Chemical Physics), **Tatiana Shavrina** (Sberbank) and **Joscha Bach** (MIT Media Lab). 

AGI-20

The AGI conference series is the only major conference series devoted wholly and specifically to the creation of AI systems possessing general intelligence at the human level and ultimately beyond. By gathering together active researchers in the field, for presentation of results and discussion of ideas, we accelerate our progress toward our common goal.


Multi-agent reinforcement learning (MARL) requires coordination by some means of interaction between agents to efficiently solve tasks. Interaction graphs allow reasoning about joint actions based on the local structure of interactions, but they disregard the potential impact of an agent’s action on its neighbors’ behaviors, which could rapidly alter in dynamic settings. In this paper, we thus present a novel perspective on opponent modeling in domains with only local interactions using (level-1) Graph Probabilistic Recursive Reasoning (GrPR2). Unlike previous work on recursive reasoning, each agent iteratively best-responds to other agents’ policies over all possible local interactions. Agents’ policies are approximated via a variational Bayes scheme for capturing their uncertainties, and we prove that an induced variant of Q-learning converges under self-play when there exists only one Nash equilibrium. In cooperative settings, we further devise a variational lower bound on the likelihood of each agent's optimality. Opposed to other models, optimizing the resulting objective prevents each agent from attaining an unrealistic modelling of others, and yields an exact tabular Q-iteration method that holds convergence guarantees. Then, we deepen the recursion to level-k via Cognitive Hierarchy GrPR2 (GrPR2-CH), which lets each level-k player best-respond to a mixture of strictly lower levels in the hierarchy. We prove that: (1) level-3 reasoning is the optimal hierarchical level, maximizing each agent's expected return; and (2) the weak spot of the classical CH models is that 0-level is uniformly distributed, as it may introduce policy bias. Finally, we propose a practical actor-critic scheme, and illustrate that GrPR2-CH outperforms strong MARL baselines in the particle environment.

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).


Centaurs are half-human, half-AI decision-makers where the AI's goal is to complement the human. To do so, the AI must be able to recognize the goals and constraints of the human and have the means to help them. We present a novel formulation of the interaction between the human and the AI as a sequential game where the agents are modelled using Bayesian best-response models. We show that in this case the AI's problem of helping bounded-rational humans make better decisions reduces to a Bayes-adaptive POMDP. In our simulated experiments, we consider an instantiation of our framework for humans who are subjectively optimistic about the AI's future behaviour. Our results show that when equipped with a model of the human, the AI can infer the human's bounds and nudge them towards better decisions. We discuss ways in which the machine can learn to improve upon its own limitations as well with the help of the human. We identify a novel trade-off for centaurs in partially observable tasks: for the AI's actions to be acceptable to the human, the machine must make sure their beliefs are sufficiently aligned, but aligning beliefs might be costly. We present a preliminary theoretical analysis of this trade-off and its dependence on task structure.

Best-Response Bayesian Reinforcement Learning with BA-POMDPs for Centaurs


Despite recent breakthroughs for learning a rich set of behaviors in simulated tasks, reinforcement learning agents are not yet in widespread use in the real world where rewards are naturally sparse. In fact, efficient exploration remains a key challenge in sparse-reward tasks as it requires quickly finding informative and task-relevant experiences. While cloning behaviors provided by an expert is a promising approach to the exploration problem, learning from a fixed set of demonstrations may be impracticable due to lack of state coverage or distribution mismatch - when the learner’s goal deviates from the demonstrated behaviors. Moreover, we aim to obtain a policy that can accomplish a variety of goals guided by the same set of demonstrations (i.e. without additional human effort). We present a goal-conditioned method that leverages very small sets of goal-driven demonstrations to significantly accelerate learning. Crucially, we present the concept of active goal-driven demonstrations to query the demonstrator only in hard-to-learn and uncertain regions of the state space. We evaluate our framework on a set of robot control tasks. The present work outperforms prior imitation learning approaches in most of the tasks in terms of data efficiency and average scores while reducing the amount of human effort.

Goal-driven Active Reinforcement Learning with Human Teachers


This work addresses the problem of sensing the world: how to learn a multimodal representation of a reinforcement learning agent's environment that allows the execution of tasks under incomplete perceptual conditions. To address such problem, we argue for hierarchy in the design of representation models and contribute with a novel multimodal representation model, MUSE. The proposed model learns hierarchical representations: low-level modality-specific representations, encoded from raw observation data, and a high-level multimodal representation, encoding joint-modality information to allow robust state estimation. We employ MUSE as the sensory representation model of deep reinforcement learning agents provided with multimodal observations in Atari games. We perform a comparative study over different designs of reinforcement learning agents, showing that MUSE allows agents to perform tasks under incomplete perceptual experience with minimal performance loss. Finally, we evaluate the performance of MUSE in literature-standard multimodal scenarios with higher number and more complex modalities, showing that it outperforms state-of-the-art multimodal variational autoencoders in single and cross-modality generation.

How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents


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.

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


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.

Optimizing Multi-Agent Coordination via Hierarchical Graph Probabilistic Recursive Reasoning

Downloads

Next from AAMAS 2022

Best-Response Bayesian Reinforcement Learning with BA-POMDPs for Centaurs

Similar lecture

The Dynamics of Growing Symbols: A Ludics Approach to Language Design by Autonomous Agents

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Optimizing Multi-Agent Coordination via Hierarchical Graph Probabilistic Recursive Reasoning

.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

Best-Response Bayesian Reinforcement Learning with BA-POMDPs for Centaurs

Similar lecture

The Dynamics of Growing Symbols: A Ludics Approach to Language Design by Autonomous Agents

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads