Laser Learning Environment: A new environment for coordination-critical multi-agent tasks

We introduce the Laser Learning Environment (LLE), a collaborative multi-agent reinforcement learning environment in which coordination is central. In LLE, agents depend on each other to make progress (interdependence), must jointly take specific sequences of actions to succeed (perfect coordination), and accomplishing those joint actions does not yield any intermediate reward (zero-incentive dynamics). The challenge of such problems lies in the difficulty of escaping state space bottlenecks caused by interdependence steps since escaping those bottlenecks is not rewarded. We test multiple state-of-the-art value-based MARL algorithms against LLE and show that they consistently fail at the collaborative task because of their inability to escape state space bottlenecks, even though they successfully achieve perfect coordination. We show that Q-learning extensions such as prioritized experience replay and n-steps return hinder exploration in environments with zero-incentive dynamics, and find that intrinsic curiosity with random network distillation is not sufficient to escape those bottlenecks. We demonstrate the need for novel methods to solve this problem and the relevance of LLE as cooperative MARL benchmark.

Mitigating Biases in Collective Decision-Making: Enhancing Performance in the Face of Fake News

Individual and social biases undermine the effectiveness of human advisers by inducing judgment errors which can disadvantage protected groups. In this paper, we study the influence these biases can have in the pervasive problem of fake news by evaluating human participants' capacity to identify false headlines. By focusing on headlines involving sensitive characteristics, we gather a comprehensive dataset to explore how human responses are shaped by their biases. Our analysis reveals recurring individual biases and their permeation into collective decisions. We show that demographic factors, headline categories, and the manner in which information is presented significantly influence errors in human judgment. We then use our collected data as a benchmark problem on which we evaluate the efficacy of adaptive aggregation algorithms. In addition to their improved accuracy, our results highlight the interactions between the emergence of collective intelligence and the mitigation of participant biases.

Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making

Experts advising decision-makers are likely to display expertise which varies as a function of the problem instance. In practice, this may lead to sub-optimal or discriminatory decisions against minority cases. In this work we model such changes in depth and breadth of knowledge as a partitioning of the problem space into regions of differing expertise. We provide here new algorithms that explicitly consider and adapt to the relationship between problem instances and experts' knowledge. We first propose and highlight the drawbacks of a naive approach based on nearest neighbor queries. To address these drawbacks we then introduce a novel algorithm - expertise trees - that constructs decision trees enabling the learner to select appropriate models. We provide theoretical insights and empirically validate the improved performance of our novel approach on a range of problems for which existing methods proved to be inadequate.

ACROCPoLis: A Descriptive Framework for Making Sense of Fairness

Fairness is central to the ethical and responsible development and use of AI systems, with a large number of frameworks and formal notions of algorithmic fairness being available. However, many of the fairness solutions proposed revolve around technical considerations and not the needs of and consequences for the most impacted communities. We therefore want to take the focus away from definitions and allow for the inclusion of societal and relational aspects to represent how the effects of AI systems impact and are experienced by individuals and social groups. In this paper, we do this by means of proposing the ACROCPoLis framework to represent allocation processes with a modeling emphasis on fairness aspects. The framework provides a shared vocabulary in which the factors relevant to fairness assessments for different situations and procedures are made explicit, as well as their interrelationships. This enables us to compare analogous situations, to highlight the differences in dissimilar situations, and to capture differing interpretations of the same situation by different stakeholders.

Dealing with Expert Bias in Collective Decision-Making

Quite some real-world problems can be formulated as decision-making problems wherein one must repeatedly make an appropriate choice from a set of alternatives. Expert judgements, whether human or artificial, can help in taking correct decisions, especially when exploration of alternative solutions is costly. As expert opinions might deviate, the problem of finding the right alternative can be approached as a collective decision making problem (CDM). Current state-of-the-art approaches to solve CDM are limited by the quality of the best expert in the group, and perform poorly if experts are not qualified or if they are overly biased, thus potentially derailing the decision-making process. In this paper, we propose a new algorithmic approach based on contextual multi-armed bandit problems (CMAB) to identify and counteract such biased expertises. We explore homogeneous, heterogeneous and polarised expert groups and show that this approach is able to effectively exploit the collective expertise, irrespective of whether the provided advice is directly conducive to good performance, outperforming state-of-the-art methods, especially when the quality of the provided expertise degrades. Our novel CMAB-inspired approach achieves a higher final performance and does so while converging more rapidly than previous adaptive algorithms, especially when heterogeneous expertise is readily available.

Voluntary safety commitments provide an escape from over-regulation in AI development

With the introduction of Artificial Intelligence (AI) and related technologies in our daily lives, fear and anxiety about their misuse as well as the hidden biases in their creation have led to a demand for regulation to address such issues. Yet blindly regulating an innovation process that is not well understood, may stifle this process and reduce benefits that society may gain from the generated technology, even under the best intentions. In this paper, starting from a baseline model that captures the fundamental dynamics of a race for domain supremacy using AI technology, we demonstrate how socially unwanted outcomes may be produced when sanctioning is applied unconditionally to risk-taking, i.e. potentially unsafe, behaviours. As an alternative to resolve the detrimental effect of over-regulation, we propose a voluntary commitment approach wherein technologists have the freedom of choice between independently pursuing their course of actions or establishing binding agreements to act safely, with sanctioning of those that do not abide to what they pledged. Overall, this work reveals for the first time how voluntary commitments, with sanctions either by peers or an institution, leads to socially beneficial outcomes in all scenarios envisageable in a short-term race towards domain supremacy through AI technology. These results are directly relevant for the design of governance and regulatory policies that aim to ensure an ethical and responsible AI technology development process.

AI Development Race Can Be Mediated on Heterogeneous Networks

The field of Artificial Intelligence (AI) has been introducing a certain level of anxiety in research, business and also policy. Tensions are further heightened by an AI race narrative which makes many stakeholders fear that they might be missing out. Whether real or not, a belief in this narrative may be detrimental as some stakeholders will feel obliged to cut corners on safety precautions or ignore societal consequences. Starting from a game-theoretical model describing an idealised technology race in a well-mixed world, here we investigate how different interaction structures among race participants can alter collective choices and requirements for regulatory actions. Our findings indicate that, when participants portray a strong diversity in terms of connections and peer-influence (e.g., when scale-free networks shape interactions among parties), the conflicts that exist in homogeneous settings are significantly reduced, thereby lessening the need for regulatory actions. Furthermore, our results suggest that technology governance and regulation may profit from the world's patent heterogeneity and inequality among firms and nations to design and implement meticulous interventions on a minority of participants capable of influencing an entire population towards an ethical and sustainable use of AI.

Mediating Artificial Intelligence Developments through Negative and Positive Incentives

The field of Artificial Intelligence (AI) is going through a period of great expectations, introducing a certain level of anxiety in research, business and also policy. This anxiety is further energised by an AI race narrative that makes people believe they might be missing out. Whether real or not, a belief in this narrative may be detrimental as some stake-holders will feel obliged to cut corners on safety precautions, or ignore societal consequences just to "win". Starting from a baseline model that describes a broad class of technology races where winners draw a significant benefit compared to others (such as AI advances, patent race, pharmaceutical technologies), we investigate here how positive (rewards) and negative (punishments) incentives may beneficially influence the outcomes. We uncover conditions in which punishment is either capable of reducing the development speed of unsafe participants or has the capacity to reduce innovation through over-regulation. Alternatively, we show that, in several scenarios, rewarding those that follow safety measures may increase the development speed while ensuring safe choices. Moreover, in {the latter} regimes, rewards do not suffer from the issue of over-regulation as is the case for punishment. Overall, our findings provide valuable insights into the nature and kinds of regulatory actions most suitable to improve safety compliance in the contexts of both smooth and sudden technological shifts.

Modelling the Safety and Surveillance of the AI Race

Innovation, creativity, and competition are some of the fundamental underlying forces driving the advances in Artificial Intelligence (AI). This race for technological supremacy creates a complex ecology of choices that may lead to negative consequences, in particular, when ethical and safety procedures are underestimated or even ignored. Here we resort to a novel game theoretical framework to describe the ongoing AI bidding war, also allowing for the identification of procedures on how to influence this race to achieve desirable outcomes. By exploring the similarities between the ongoing competition in AI and evolutionary systems, we show that the timelines in which AI supremacy can be achieved play a crucial role for the evolution of safety prone behaviour and whether influencing procedures are required. When this supremacy can be achieved in a short term (near AI), the significant advantage gained from winning a race leads to the dominance of those who completely ignore the safety precautions to gain extra speed, rendering of the presence of reciprocal behavior irrelevant. On the other hand, when such a supremacy is a distant future, reciprocating on others' safety behaviour provides in itself an efficient solution, even when monitoring of unsafe development is hard. Our results suggest under what conditions AI safety behaviour requires additional supporting procedures and provide a basic framework to model them.

Dynamic Weights in Multi-Objective Deep Reinforcement Learning

Many real-world decision problems are characterized by multiple objectives which must be balanced based on their relative importance. In the dynamic weights setting this relative importance changes over time, as recognized by Natarajan and Tadepalli (2005) who proposed a tabular Reinforcement Learning algorithm to deal with this problem. However, this earlier work is not feasible for reinforcement learning settings in which the input is high-dimensional, necessitating the use of function approximators, such as neural networks. We propose two novel methods for multi-objective RL with dynamic weights, a multi-network approach and a single-network approach that conditions on the weights. Due to the inherent non-stationarity of the dynamic weights setting, standard experience replay techniques are insufficient. We therefore propose diverse experience replay, a framework to maintain a diverse set of experiences in the replay buffer, and show how it can be applied to make experience replay relevant in multi-objective RL. To evaluate the performance of our algorithms we introduce a new benchmark called the Minecart problem. We show empirically that our algorithms outperform more naive approaches. We also show that, while there are significant differences between many small changes in the weights opposed to sparse larger changes, the conditioned network with diverse experience replay consistently outperforms the other algorithms.