We consider a multi-agent resource allocation setting in which an agent's utility may decrease or increase when an item is allocated. We take the group envy-freeness concept that is well-established in the literature and present stronger and relaxed versions that are especially suitable for the allocation of indivisible items. Of particular interest is a concept called group envy-freeness up to one item (GEF1). We then present a clear taxonomy of the fairness concepts. We study which fairness concepts guarantee the existence of a fair allocation under which preference domain. For two natural classes of additive utilities, we design polynomial-time algorithms to compute a GEF1 allocation. We also prove that checking whether a given allocation satisfies GEF1 is coNP-complete when there are either only goods, only chores or both.

In distributed reinforcement learning, it is common to exchange the experience memory of each agent and thereby collectively train their local models. The experience memory, however, contains all the preceding state observations and their corresponding policies of the host agent, which may violate the privacy of the agent. To avoid this problem, in this work, we propose a privacy-preserving distributed reinforcement learning (RL) framework, termed federated reinforcement distillation (FRD). The key idea is to exchange a proxy experience memory comprising a pre-arranged set of states and time-averaged policies, thereby preserving the privacy of actual experiences. Based on an advantage actor-critic RL architecture, we numerically evaluate the effectiveness of FRD and investigate how the performance of FRD is affected by the proxy memory structure and different memory exchanging rules.

Instability and slowness are two main problems in deep reinforcement learning. Even if proximal policy optimization is the state of the art, it still suffers from these two problems. We introduce an improved algorithm based on proximal policy optimization (PPO), mixed distributed proximal policy optimization (MDPPO), and show that it can accelerate and stabilize the training process. In our algorithm, multiple different policies train simultaneously and each of them controls several identical agents that interact with environments. Actions are sampled by each policy separately as usual but the trajectories for training process are collected from all agents, instead of only one policy. We find that if we choose some auxiliary trajectories elaborately to train policies, the algorithm will be more stable and quicker to converge especially in the environments with sparse rewards.

While many multiagent algorithms are designed for homogeneous systems (i.e. all agents are identical), there are important applications which require an agent to coordinate its actions without knowing a priori how the other agents behave. One method to make this problem feasible is to assume that the other agents draw their latent policy (or type) from a specific set, and that a domain expert could provide a specification of this set, albeit only a partially correct one. Algorithms have been proposed by several researchers to compute posterior beliefs over such policy libraries, which can then be used to determine optimal actions. In this paper, we provide theoretical guidance on two central design parameters of this method: Firstly, it is important that the user choose a posterior which can learn the true distribution of latent types, as otherwise suboptimal actions may be chosen. We analyse convergence properties of two existing posterior formulations and propose a new posterior which can learn correlated distributions. Secondly, since the types are provided by an expert, they may be inaccurate in the sense that they do not predict the agents' observed actions. We provide a novel characterisation of optimality which allows experts to use efficient model checking algorithms to verify optimality of types.

Human culture is uniquely cumulative and open-ended. Using a computational model of cultural evolution in which neural network based agents evolve ideas for actions through invention and imitation, we tested the hypothesis that this is due to the capacity for recursive recall. We compared runs in which agents were limited to single-step actions to runs in which they used recursive recall to chain simple actions into complex ones. Chaining resulted in higher cultural diversity, open-ended generation of novelty, and no ceiling on the mean fitness of actions. Both chaining and no-chaining runs exhibited convergence on optimal actions, but without chaining this set was static while with chaining it was ever-changing. Chaining increased the ability to capitalize on the capacity for learning. These findings show that the recursive recall hypothesis provides a computationally plausible explanation of why humans alone have evolved the cultural means to transform this planet.

We present some results concerning the dialogue behavior and inferred sentiment of a group of older adults interacting with a computer-based avatar. Our avatar is unique in its ability to hold natural dialogues on a wide range of everyday topics---27 topics in three groups, developed with the help of gerontologists. The three groups vary in ``degrees of intimacy", and as such in degrees of difficulty for the user. Each participant interacted with the avatar for 7-9 sessions over a period of 3-4 weeks; analysis of the dialogues reveals correlations such as greater verbosity for more difficult topics, increasing verbosity with successive sessions, especially for more difficult topics, stronger sentiment on topics concerned with life goals rather than routine activities, and stronger self-disclosure for more intimate topics. In addition to their intrinsic interest, these results also reflect positively on the sophistication of our dialogue system.

These MARL Reinforcement Learning is a subset of Machine Learning by models use training policy coordination mechanisms to which agents can become proficient in functioning by itself in minimize the impact of the training tasks.

The machines have proven their superiority in one-on-one games like chess and go, and even poker -- but in complex multiplayer versions of the card game humans have retained their edge… until now. An evolution of the last AI agent to flummox poker pros individually is now decisively beating them in championship-style 6-person game. As documented in a paper published in the journal Science today, the CMU/Facebook collaboration they call Pluribus reliably beats five professional poker players in the same game, or one pro pitted against five independent copies of itself. It's a major leap forward in capability for the machines, and amazingly is also far more efficient than previous agents as well. One-on-one poker is a weird game, and not a simple one, but the zero-sum nature of it (whatever you lose, the other player gets) makes it susceptible to certain strategies in which computer able to calculate out far enough can put itself at an advantage.

To understand and explain process behaviour we need to be able to see it, and decide its significance, i.e. be able to tell a story about its behaviours. This paper describes a few of the modelling challenges that underlie monitoring and observation of processes in IT, by human or by software. The topic of the observability of systems has been elevated recently in connection with computer monitoring and tracing of processes for debugging and forensics. It raises the issue of well-known principles of measurement, in bounded contexts, but these issues have been left implicit in the Computer Science literature. This paper aims to remedy this omission, by laying out a simple promise theoretic model, summarizing a long standing trail of work on the observation of distributed systems, based on elementary distinguishability of observations, and classical causality, with history. Three distinct views of a system are sought, across a number of scales, that described how information is transmitted (and lost) as it moves around the system, aggregated into journals and logs.

Many real-world human behaviors can be characterized as a sequential decision making processes, such as urban travelers choices of transport modes and routes (Wu et al. 2017). Differing from choices controlled by machines, which in general follows perfect rationality to adopt the policy with the highest reward, studies have revealed that human agents make sub-optimal decisions under bounded rationality (Tao, Rohde, and Corcoran 2014). Such behaviors can be modeled using maximum causal entropy (MCE) principle (Ziebart 2010). In this paper, we define and investigate a general reward trans-formation problem (namely, reward advancement): Recovering the range of additional reward functions that transform the agent's policy from original policy to a predefined target policy under MCE principle. We show that given an MDP and a target policy, there are infinite many additional reward functions that can achieve the desired policy transformation. Moreover, we propose an algorithm to further extract the additional rewards with minimum "cost" to implement the policy transformation.