相关论文: Making an Example: Signalling Threat in the Evolut…

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…

Addressing both natural and societal challenges requires collective cooperation. Studies on collective-risk social dilemmas have shown that individual decisions are influenced by the perceived risk of collective failure. However, existing…

In this paper, the total payoff of each agent is regulated to reduce the heterogeneity of the distribution of the total payoffs. It is found there is an optimal regulation strength where the fraction of cooperation is prominently promoted,…

Solving a reinforcement learning problem typically involves correctly prespecifying the reward signal from which the algorithm learns. Here, we approach the problem of reward signal design by using an evolutionary approach to perform a…

When biological communities use signaling structures for complex coordination, 'free-riders' emerge. The free-riding agents do not contribute to the community resources (signals), but exploit them. Most models of such 'selfish' behavior…

Multi-agent social dilemmas, such as the tragedy of the commons, capture settings where individual incentives conflict with collective well-being, making these systems highly vulnerable to collapse under disruptions. In this context, this…

Here we study the effects of adopting different strategies against different opponent instead of adopting the same strategy against all of them in the prisoner dilemma structured in well-mixed populations. We consider an evolutionary…

We study the evolution of cooperation in the spatial prisoner's dilemma game, where besides unconditional cooperation and defection, tit-for-tat, win-stay-lose-shift and extortion are the five competing strategies. While pairwise imitation…

Whether or not to change strategy depends not only on the personal success of each individual, but also on the success of others. Using this as motivation, we study the evolution of cooperation in games that describe social dilemmas, where…

Social intelligence, the ability to navigate complex interpersonal interactions, presents a fundamental challenge for language agents. Training such agents via reinforcement learning requires solving the credit assignment problem:…

Cooperation is a difficult proposition in the face of Darwinian selection. Those that defect have an evolutionary advantage over cooperators who should therefore die out. However, spatial structure enables cooperators to survive through the…

Building ethical machines may involve bestowing upon them the emotional capacity to self-evaluate and repent on their actions. While apologies represent potential strategic interactions, the explicit evolution of guilt as a behavioural…

Causal models bring many benefits to decision-making systems (or agents) by making them interpretable, sample-efficient, and robust to changes in the input distribution. However, spurious correlations can lead to wrong causal models and…

Artificial Intelligence represents many things: a new market to conquer or a quality label for tech companies, a threat for traditional industries, a menace for democracy, or a blessing for our busy everyday life. The press abounds in…

Extortion strategies can dominate any opponent in an iterated prisoner's dilemma game. But if players are able to adopt the strategies performing better, extortion becomes widespread and evolutionary unstable. It may sometimes act as a…

Economic experiments reveal that humans value cooperation and fairness. Punishing unfair behavior is therefore common, and according to the theory of strong reciprocity, it is also directly related to rewarding cooperative behavior.…

AI systems have the potential to produce both benefits and harms, but without rigorous and ongoing adversarial evaluation, AI actors will struggle to assess the breadth and magnitude of the AI risk surface. Researchers from the field of…

We consider a spatial model of the emergence of cooperation with synchronous births and deaths. Agents bear a tag and interact with their neighbors by playing the prisoner's dilemma game with strategies depending on their own and opponent's…

We study the evolution of cooperation in structured populations within popular models of social dilemmas, whereby simple coevolutionary rules are introduced that may enhance players abilities to enforce their strategy on the opponent.…

This paper studies a preference evolution model in which a population of agents are matched to play a sequential prisoner's dilemma in an incomplete information environment. An institution can design an incentive-compatible screening…