United Kingdom

We address the problem of multiagent credit assignment  in a large scale multiagent system. Difference rewards (DRs) are an effective tool to tackle this problem, but their exact computation is known to be challenging even for small number of agents. We propose a scalable method to compute difference rewards based on aggregate information in a multiagent system with large number of agents by exploiting the symmetry present in several practical applications. Empirical evaluation on two multiagent domains  air-traffic control and cooperative navigation, shows better solution quality than previous approaches.

AAMAS 2021

Approximate Difference Rewards for Scalable Multigent Reinforcement Learning

AAMAS is the largest and most influential conference in the area of agents and multiagent systems, bringing together researchers and practitioners in all areas of agent technology and providing and internationally renowned high-profile forum for publishing and finding out about the latest developments in the field. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).  

![](https://assets.underline.io/uploads/markdown_image/1/image/ce4604bd54468a006164d16e080204fb.jpg)

Please click on the button below to register for this event.

If you are registered and see this page please check the account email you are logged in with. It must be the same as for the registration.

If you still have trouble accessing the contact please contact support at aamas2021@underline.io 

poster

We model interpretive blindness, a type of epistemic bias that poses a problem for learning from testimony, in which one acquires information from text or conversation but lacks direct access to ground truth. Interpretive blindness arises when a co-dependence between background beliefs and interpretation leads to a dynamic process of bias hardening that impedes or precludes learning. We argue that when bodies of data are argumentatively complete, even constraints from hierarchical Bayesian learning designed to promote good epistemic practices will fail to stop interpretive blindness.

Interpretive Blindness and the Impossibility of Learning from Testimony

We present the first explicit-state method for analysing and ensuring the safety of DRL agents for Atari games. Our method only requires access to the emulator. We give a suite of 42 properties that characterise "safe behaviour" for 31 games. We evaluate the safety of the best available DRL agents which, as our experiments show, violate most of our properties. We propose a countermeasure that implements shielding using bounded explicit-state exploration. Our method improved their overall safety, producing the safest DRL agents for Atari games currently available.

Shielding Atari Games with Bounded Prescience

In this work we introduce an interactive machine teaching approach that teaches a classification task to the learner. Our adaptive approach - Feature Importance Teaching (FIT) - does not assume perfect knowledge about the learner, as most machine teaching approaches do. It chooses, online, which sample to show next, as it updates the learner's model based on feedback from the student on the weights attributed to the features. We present simulated results where the student has a different prior knowledge from the one assumed by the teacher. The results have shown that our teaching approach can mitigate this mismatch and lead to a significantly faster learning curve than the ones obtained in conditions where the teacher randomly selects the samples or does not consider this feedback from the student.

Teaching Unknown Learners to Classify via Feature Importance

This paper is concerned with designing purpose in autonomous robots for open-ended learning settings. Unconstrained human robot interaction situations and robotic systems that must operate in dynamic multi-robot scenarios are paradigmatic examples of open-endedness. An approach to the appropriate design and engineering of motivational structures to endow robots with a particular purpose is proposed and tested. This approach focuses on the drive structure and how it can be made to autonomously adapt to changing circumstances. Specifically, a simple evolutionary strategy for the autonomous regulation of multiple drives in order to optimize long-term operation is defined. The experimental results have been obtained on a Baxter robot facing changing situations in real setups.

An Autonomous Drive Balancing Strategy for the Design of Purpose in Open-ended Learning Robots

Most existing incentive allocation approaches rely on sufficient information about users' attributes, such as their preferences, followers in the social network, and activities, to customize effective incentives. However, this may lead to failure when such knowledge is unavailable. In this light, we propose an end-to-end reinforcement learning-based framework, named Geometric Actor-Critic (GAC), to discover effective incentive allocation policies towards users in a social network. More specifically, given a limited budget, the proposed approach can extract information from a high-level network representation for learning effective incentive allocation policies. The proposed GAC only requires the topology of the social network and does not rely on any prior information about users' attributes. We use three real-world social network datasets to evaluate the performance of the proposed GAC. The experimental results demonstrate the effectiveness of the proposed approach.

Learning Policies for Effective Incentive Allocation in Unknown Social Networks

Several frameworks for decentralized reasoning assume a junction tree agent organization (JT-org). JT-org construction involves 3 related tasks on existence recognition, construction, and environment re-decomposition, where re-decomposition incurs loss of JT-org linked privacy, including privacy on agent, topology, private and shared variables. We propose a novel algorithm DAER that accomplishes all 3 tasks distributively. For Tasks 1 and 2, DAER incurs no loss of JT-org linked privacy.For Task 3, it incurs significantly less privacy loss than existing JT-org construction methods. Its performance is formally analyzed and empirically evaluated.

Constructing Junction Tree Agent Organization with Privacy (JAAMAS Track)

Creating incentives for cooperation is a challenge in natural and artificial systems.   One potential answer is reputation, whereby agents trade the immediate cost of cooperation for the future benefits of having a good reputation.   Game theoretical models have shown that specific social norms can make cooperation stable, but how agents can independently learn to establish effective reputation mechanisms on their own is less understood. We use a simple model of reinforcement learning to show that reputation mechanisms generate two coordination problems: agents need to learn how to coordinate on the meaning of existing reputations and collectively agree on a social norm to assign reputations to others based on their behavior. These coordination problems exhibit multiple equilibria, some of which effectively establish cooperation. When we train agents with a standard Q-learning algorithm in an environment with the presence of reputation mechanisms, convergence to undesirable equilibria is widespread. We propose two mechanisms to alleviate this: (i) seeding a proportion of the system with fixed agents that steer others towards good equilibria; and (ii), intrinsic rewards based on the idea of introspection, i.e., augmenting agents' rewards by an amount proportionate to the performance of their own strategy against themselves. A combination of these simple mechanisms is successful in stabilizing cooperation, even in a fully decentralized version of the problem where agents learn to use and assign reputations simultaneously. We show how our results relate to the literature in Evolutionary Game Theory, and discuss implications for artificial, human and hybrid systems, where reputations can be used as a way to establish trust and cooperation.

Cooperation and Reputation Dynamics with Reinforcement Learning

Can artificial agents benefit from human conventions? Human societies manage to successfully self-organize and resolve the tragedy of the commons in common-pool resources, in spite of the bleak prediction of non-cooperative game theory. On top of that, real-world problems are inherently large-scale and of low observability. One key concept that facilitates human coordination in such settings is the use of conventions. Inspired by human behavior, we investigate the learning dynamics and emergence of temporal conventions, focusing on common-pool resources. Extra emphasis was given in designing a realistic evaluation setting: (a) environment dynamics are modeled on real-world fisheries, (b) we assume decentralized learning, where agents can observe only their own history, and (c) we run large-scale simulations (up to 64 agents).

Improved Cooperation by Exploiting a Common Signal

We study how wealth inequality influences behavioral dynamics in groups of independent reinforcement learners facing a threshold public goods dilemma with uncertain returns. The game allows individuals to contribute or not to a common pool to reduce their chances of future losses. The non-linearity introduced by the threshold, the stochasticity introduced by the risk and the wealth heterogeneity of players result in a game setting with multiple equilibria. We find that the learners' dynamics in this case play a major role in determining the attained equilibrium point. Our results suggest that, under individual-based learning, wealth inequality can have sizable effects on the emerging collective behaviors, decreasing the overall chances of group success. Moreover, we compute the class-based Nash equilibria (i.e., where same wealth-class agents are assumed to play the same strategy) for this game and compare the performance of groups composed of independent learning agents with the performance obtained under the payoff maximizing class-based Nash equilibrium. We find that the learned strategies never really match optimal performance for all tested values of risk.

Cooperation between Independent Reinforcement Learners under Wealth Inequality and Collective Risks

High-performing teams learn effective communication strategies to judiciously share information and reduce the cost of communication overhead. Within multi-agent reinforcement learning, synthesizing effective policies requires reasoning about when to communicate, whom to communicate with, and how to process messages. We propose a novel multi-agent reinforcement learning algorithm, Multi-Agent Graph-attentIon Communication (MAGIC), with a graph-attention communication protocol in which we learn 1) a Scheduler to help with the problems of when to communicate and whom to address messages to, and 2) a Message Processor using Graph Attention Networks (GATs) with dynamic graphs to deal with communication signals. The Scheduler consists of a graph attention encoder and a differentiable attention mechanism, which outputs dynamic, differentiable graphs to the Message Processor, which enables the Scheduler and Message Processor to be trained end-to-end. We evaluate our approach on a variety of cooperative tasks, including Google Research Football. Our method outperforms baselines across all domains, achieving ~10.5% increase in reward in the most challenging domain. We also show MAGIC communicates $27.4%$ more efficiently on average than baselines, is robust to stochasticity, and scales to larger state-action spaces. Finally, we demonstrate MAGIC on a physical, multi-robot testbed.

Approximate Difference Rewards for Scalable Multigent Reinforcement Learning

Next from AAMAS 2021

Interpretive Blindness and the Impossibility of Learning from Testimony

Similar lecture

Tunable Behaviours in Sequential Social Dilemmas using Multi-Objective Reinforcement Learning