Blame attribution is one of the key aspects of accountable decision making, as it provides means to quantify the responsibility of an agent for a decision making outcome. In this paper, we study blame attribution in the context of cooperative multi-agent sequential decision making. As a particular setting of interest, we focus on cooperative decision making formalized by Multi-Agent Markov Decision Processes (MMDP), and we analyze different blame attribution methods derived from or inspired by existing concepts in cooperative game theory. We formalize desirable properties of blame attribution in the setting of interest, and we analyze the relationship between these properties and the studied blame attribution methods. Interestingly, we show that some of the well known blame attribution methods, such as Shapley value, are not performance-incentivizing, while others, such as Banzhaf index, may over-blame agents. To mitigate these value misalignment and fairness issues, we introduce a novel blame attribution method, unique in the set of properties it satisfies, which trade-offs explanatory power (by under-blaming agents) for the aforementioned properties. We further show how to account for uncertainty about agents' decision making policies, and we experimentally: a) validate the qualitative properties of the studied blame attribution methods, and b) analyze their robustness to uncertainty.

One of the difficulties in training dialogue systems is the lack of training data. We explore the possibility of creating dialogue data through the interaction between a dialogue system and a user simulator. Our goal is to develop a modelling framework that can incorporate new dialogue scenarios through self-play between the two agents. In this framework, we first pre-train the two agents on a collection of source domain dialogues, which equips the agents to converse with each other via natural language. With further fine-tuning on a small amount of target domain data, the agents continue to interact with the aim of improving their behaviors using reinforcement learning with structured reward functions. In experiments on the MultiWOZ dataset, two practical transfer learning problems are investigated: 1) domain adaptation and 2) single-to-multiple domain transfer. We demonstrate that the proposed framework is highly effective in bootstrapping the performance of the two agents in transfer learning. We also show that our method leads to improvements in dialogue system performance on complete datasets.

Cooperative multi-agent systems are being widely used in variety of areas. Interaction between agents would bring positive points, including reducing costs of operating, high scalability, and facilitating parallel processing. These systems pave the way for handling large-scale, unknown, and dynamic environments. However, learning in these environments has become a prominent challenge in different applications. These challenges include the effect of size of search space on learning time, inappropriate cooperation among agents, and the lack of proper coordination among agents' decisions. Moreover, reinforcement learning algorithms may suffer from long time of convergence in these problems. In this paper, a communication framework using knowledge transfer concepts is introduced to address such challenges in the herding problem with large state space. To handle the problems of convergence, knowledge transfer has been utilized that can significantly increase the efficiency of reinforcement learning algorithms. Coordination between the agents is carried out through a head agent in each group of agents and a coordinator agent respectively. The results demonstrate that this framework could indeed enhance the speed of learning and reduce convergence time.

When agents are swarmed to carry out a mission, there is often a sudden failure of some of the agents observed from the command base. It is generally difficult to distinguish whether the failure is caused by actuators (hypothesis, $h_a$) or sensors (hypothesis, $h_s$) solely by the communication between the command base and the concerning agent. By making a collision to the agent by another, we would be able to distinguish which hypothesis is likely: For $h_a$, we expect to detect corresponding displacements while for $h_a$ we do not. Such swarm strategies to grasp the situation are preferably to be generated autonomously by artificial intelligence (AI). Preferable actions ($e.g.$, the collision) for the distinction would be those maximizing the difference between the expected behaviors for each hypothesis, as a value function. Such actions exist, however, only very sparsely in the whole possibilities, for which the conventional search based on gradient methods does not make sense. Instead, we have successfully applied the reinforcement learning technique, achieving the maximization of such a sparse value function. The machine learning actually concluded autonomously the colliding action to distinguish the hypothesises. Getting recognized an agent with actuator error by the action, the agents behave as if other ones want to assist the malfunctioning one to achieve a given mission.

If an agent, or a coalition of agents, has a strategy, knows that she has a strategy, and knows what the strategy is, then she has a know-how strategy. Several modal logics of coalition power for know-how strategies have been studied before. The contribution of the article is three-fold. First, it proposes a new class of know-how strategies that depend on the intelligence information about the opponents' actions. Second, it shows that the coalition power modality for the proposed new class of strategies cannot be expressed through the standard know-how modality. Third, it gives a sound and complete logical system that describes the interplay between the coalition power modality with intelligence and the distributed knowledge modality in games with imperfect information.

Exploration is critical for good results in deep reinforcement learning and has attracted much attention. However, existing multi-agent deep reinforcement learning algorithms still use mostly noise-based techniques. Very recently, exploration methods that consider cooperation among multiple agents have been developed. However, existing methods suffer from a common challenge: agents struggle to identify states that are worth exploring, and hardly coordinate exploration efforts toward those states. To address this shortcoming, in this paper, we propose cooperative multi-agent exploration (CMAE): agents share a common goal while exploring. The goal is selected from multiple projected state spaces via a normalized entropy-based technique. Then, agents are trained to reach this goal in a coordinated manner. We demonstrate that CMAE consistently outperforms baselines on various tasks, including a sparse-reward version of the multiple-particle environment (MPE) and the Starcraft multi-agent challenge (SMAC).

In this paper we introduce a simple modal logic framework to reason about the expertise of an information source. In the framework, a source is an expert on a proposition $p$ if they are able to correctly determine the truth value of $p$ in any possible world. We also consider how information may be false, but true after accounting for the lack of expertise of the source. This is relevant for modelling situations in which information sources make claims beyond their domain of expertise. We use non-standard semantics for the language based on an expertise set with certain closure properties. It turns out there is a close connection between our semantics and S5 epistemic logic, so that expertise can be expressed in terms of knowledge at all possible states. We use this connection to obtain a sound and complete axiomatisation.

Can artificial agents learn to assist others in achieving their goals without knowing what those goals are? Generic reinforcement learning agents could be trained to behave altruistically towards others by rewarding them for altruistic behaviour, i.e., rewarding them for benefiting other agents in a given situation. Such an approach assumes that other agents' goals are known so that the altruistic agent can cooperate in achieving those goals. However, explicit knowledge of other agents' goals is often difficult to acquire. Even assuming such knowledge to be given, training of altruistic agents would require manually-tuned external rewards for each new environment. Thus, it is beneficial to develop agents that do not depend on external supervision and can learn altruistic behaviour in a task-agnostic manner. Assuming that other agents rationally pursue their goals, we hypothesize that giving them more choices will allow them to pursue those goals better. Some concrete examples include opening a door for others or safeguarding them to pursue their objectives without interference. We formalize this concept and propose an altruistic agent that learns to increase the choices another agent has by maximizing the number of states that the other agent can reach in its future. We evaluate our approach on three different multi-agent environments where another agent's success depends on the altruistic agent's behaviour. Finally, we show that our unsupervised agents can perform comparably to agents explicitly trained to work cooperatively. In some cases, our agents can even outperform the supervised ones.

In the peer selection problem a group of agents must select a subset of themselves as winners for, e.g., peer-reviewed grants or prizes. Here, we take a Condorcet view of this aggregation problem, i.e., that there is a ground-truth ordering over the agents and we wish to select the best set of agents, subject to the noisy assessments of the peers. Given this model, some agents may be unreliable, while others might be self-interested, attempting to influence the outcome in their favour. In this paper we extend PeerNomination, the most accurate peer reviewing algorithm to date, into WeightedPeerNomination, which is able to handle noisy and inaccurate agents. To do this, we explicitly formulate assessors' reliability weights in a way that does not violate strategyproofness, and use this information to reweight their scores. We show analytically that a weighting scheme can improve the overall accuracy of the selection significantly. Finally, we implement several instances of reweighting methods and show empirically that our methods are robust in the face of noisy assessments.

Markov Decision Processes (MDPs) are an effective way to formally describe many Machine Learning problems. In fact, recently MDPs have also emerged as a powerful framework to model financial trading tasks. For example, financial MDPs can model different market scenarios. However, the learning of a (near-)optimal policy for each of these financial MDPs can be a very time-consuming process, especially when nothing is known about the policy to begin with. An alternative approach is to find a similar financial MDP for which we have already learned its policy, and then reuse such policy in the learning of a new policy for a new financial MDP. Such a knowledge transfer between market scenarios raises several issues. On the one hand, how to measure the similarity between financial MDPs. On the other hand, how to use this similarity measurement to effectively transfer the knowledge between financial MDPs. This paper addresses both of these issues. Regarding the first one, this paper analyzes the use of three similarity metrics based on conceptual, structural and performance aspects of the financial MDPs. Regarding the second one, this paper uses Probabilistic Policy Reuse to balance the exploitation/exploration in the learning of a new financial MDP according to the similarity of the previous financial MDPs whose knowledge is reused.