arXiv subjects

Georgios Chalkiadakis

Publications and source records attributed to Georgios Chalkiadakis.

15 recordsLinked to original sources

arXiv2026

Monte-Carlo Tree Search with Neural Network Guidance for Lane-Free Autonomous Driving

Lane-free traffic environments allow vehicles to better harness the lateral capacity of the road without being restricted to lane-keeping, thereby increasing the traffic flow rates. As such, we have a distinct and more challenging setting for autonomous driving. In this work, we consider a Monte-Carlo Tree Search (MCTS) planning approach for single-agent autonomous driving in lane-free traffic, where the associated Markov Decision Process we formulate is influenced from existing approaches tied to reinforcement learning frameworks. In addition, MCTS is equipped with a pre-trained neural network (NN) that guides the selection phase. This procedure incorporates the predictive capabilities of NNs for a more informed tree search process under computational constraints. In our experimental evaluation, we consider metrics that address both safety (through collision rates) and efficacy (through measured speed). Then, we examine: (a) the influence of isotropic state information for vehicles in a lane-free environment, resulting in nudging behaviour--vehicles' policy reacts due to the presence of faster tailing ones, (b) the acceleration of performance for the NN-guided variant of MCTS, and (c) the trade-off between computational resources and solution quality.

cs.AI↗

arXiv2025

On Altruism and Spite in Bimatrix Games

One common assumption in game theory is that any player optimizes a utility function that takes into account only its own payoff. However, it has long been observed that in real life players may adopt an altruistic or even spiteful behaviour. As such, there are numerous attempts in the economics literature that strive to explain the fact that players are not entirely selfish, but most of these works do not focus on the algorithmic implications of altruism or spite in games. In this paper, we relax the aforementioned ``self-interest'' assumption, and initiate the study of algorithmic aspects of bimatrix games -- such as the complexity and the quality of their (approximate) Nash equilibria -- under altruism or spite. We provide both a theoretical and an experimental treatment of these topics. Moreover, we demonstrate the potential for learning the degree of an opponent's altruistic/spiteful behaviour, and employing this for opponent selection and transfer of knowledge in bimatrix games.

cs.GT↗

arXiv2025

Graph Neural Networks, Deep Reinforcement Learning and Probabilistic Topic Modeling for Strategic Multiagent Settings

This paper provides a comprehensive review of mainly GNN, DRL, and PTM methods with a focus on their potential incorporation in strategic multiagent settings. We draw interest in (i) ML methods currently utilized for uncovering unknown model structures adaptable to the task of strategic opponent modeling, and (ii) the integration of these methods with Game Theoretic concepts that avoid relying on assumptions often invalid in real-world scenarios, such as the Common Prior Assumption (CPA) and the Self-Interest Hypothesis (SIH). We analyze the ability to handle uncertainty and heterogeneity, two characteristics that are very common in real-world application cases, as well as scalability. As a potential answer to effectively modeling relationships and interactions in multiagent settings, we champion the use of GNN. Such approaches are designed to operate upon graph-structured data, and have been shown to be a very powerful tool for performing tasks such as node classification and link prediction. Next, we review the domain of RL, and in particular that of multiagent deep reinforcement learning. Single-agent deep RL has been widely used for decision making in demanding game settings. Its application in multiagent settings though is hindered due to, e.g., varying relationships between agents, and non-stationarity of the environment. We describe existing relevant game theoretic solution concepts, and consider properties such as fairness and stability. Our review comes complete with a note on the literature that utilizes probabilistic topic modeling (PTM) in domains other than that of document analysis and classification. Finally, we identify certain open challenges -- specifically, the need to (i) fit non-stationary environments, (ii) balance the degrees of stability and adaptation, (iii) tackle uncertainty and heterogeneity, (iv) guarantee scalability and solution tractability.

cs.AI↗

arXiv2025

Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances

Imitation learning (IL) enables agents to acquire skills by observing and replicating the behavior of one or multiple experts. In recent years, advances in deep learning have significantly expanded the capabilities and scalability of imitation learning across a range of domains, where expert data can range from full state-action trajectories to partial observations or unlabeled sequences. Alongside this growth, novel approaches have emerged, with new methodologies being developed to address longstanding challenges such as generalization, covariate shift, and demonstration quality. In this survey, we review the latest advances in imitation learning research, highlighting recent trends, methodological innovations, and practical applications. We propose a novel taxonomy that is distinct from existing categorizations to better reflect the current state of the IL research stratum and its trends. Throughout the survey, we critically examine the strengths, limitations, and evaluation practices of representative works, and we outline key challenges and open directions for future research.

cs.LG↗

arXiv2025

Going Beyond Expert Performance via Deep Implicit Imitation Reinforcement Learning

Imitation learning traditionally requires complete state-action demonstrations from optimal or near-optimal experts. These requirements severely limit practical applicability, as many real-world scenarios provide only state observations without corresponding actions and expert performance is often suboptimal. In this paper we introduce a deep implicit imitation reinforcement learning framework that addresses both limitations by combining deep reinforcement learning with implicit imitation learning from observation-only datasets. Our main algorithm, Deep Implicit Imitation Q-Network (DIIQN), employs an action inference mechanism that reconstructs expert actions through online exploration and integrates a dynamic confidence mechanism that adaptively balances expert-guided and self-directed learning. This enables the agent to leverage expert guidance for accelerated training while maintaining capacity to surpass suboptimal expert performance. We further extend our framework with a Heterogeneous Actions DIIQN (HA-DIIQN) algorithm to tackle scenarios where expert and agent possess different action sets, a challenge previously unaddressed in the implicit imitation learning literature. HA-DIIQN introduces an infeasibility detection mechanism and a bridging procedure identifying alternative pathways connecting agent capabilities to expert guidance when direct action replication is impossible. Our experimental results demonstrate that DIIQN achieves up to 130% higher episodic returns compared to standard DQN, while consistently outperforming existing implicit imitation methods that cannot exceed expert performance. In heterogeneous action settings, HA-DIIQN learns up to 64% faster than baselines, leveraging expert datasets unusable by conventional approaches. Extensive parameter sensitivity analysis reveals the framework's robustness across varying dataset sizes and hyperparameter configurations.

cs.LG↗

arXiv2025

Value of Information-Enhanced Exploration in Bootstrapped DQN

Efficient exploration in deep reinforcement learning remains a fundamental challenge, especially in environments characterized by high-dimensional states and sparse rewards. Traditional exploration strategies that rely on random local policy noise, such as $\epsilon$-greedy and Boltzmann exploration methods, often struggle to efficiently balance exploration and exploitation. In this paper, we integrate the notion of (expected) value of information (EVOI) within the well-known Bootstrapped DQN algorithmic framework, to enhance the algorithm's deep exploration ability. Specifically, we develop two novel algorithms that incorporate the expected gain from learning the value of information into Bootstrapped DQN. Our methods use value of information estimates to measure the discrepancies of opinions among distinct network heads, and drive exploration towards areas with the most potential. We evaluate our algorithms with respect to performance and their ability to exploit inherent uncertainty arising from random network initialization. Our experiments in complex, sparse-reward Atari games demonstrate increased performance, all the while making better use of uncertainty, and, importantly, without introducing extra hyperparameters.

cs.LG↗

arXiv2025

A Novel Framework for Uncertainty-Driven Adaptive Exploration

Adaptive exploration methods propose ways to learn complex policies via alternating between exploration and exploitation. An important question for such methods is to determine the appropriate moment to switch between exploration and exploitation and vice versa. This is critical in domains that require the learning of long and complex sequences of actions. In this work, we present a generic adaptive exploration framework that employs uncertainty to address this important issue in a principled manner. Our framework includes previous adaptive exploration approaches as special cases. Moreover, we can incorporate in our framework any uncertainty-measuring mechanism of choice, for instance mechanisms used in intrinsic motivation or epistemic uncertainty-based exploration methods. We experimentally demonstrate that our framework gives rise to adaptive exploration strategies that outperform standard ones across several environments.

cs.AI↗

arXiv2025

Seldonian Reinforcement Learning for Ad Hoc Teamwork

Most offline RL algorithms return optimal policies but do not provide statistical guarantees on desirable behaviors. This could generate reliability issues in safety-critical applications, such as in some multiagent domains where agents, and possibly humans, need to interact to reach their goals without harming each other. In this work, we propose a novel offline RL approach, inspired by Seldonian optimization, which returns policies with good performance and statistically guaranteed properties with respect to predefined desirable behaviors. In particular, our focus is on Ad Hoc Teamwork settings, where agents must collaborate with new teammates without prior coordination. Our method requires only a pre-collected dataset, a set of candidate policies for our agent, and a specification about the possible policies followed by the other players -- it does not require further interactions, training, or assumptions on the type and architecture of the policies. We test our algorithm in Ad Hoc Teamwork problems and show that it consistently finds reliable policies while improving sample efficiency with respect to standard ML baselines.

cs.LG↗

arXiv2025

Conditional Max-Sum for Asynchronous Multiagent Decision Making

In this paper we present a novel approach for multiagent decision making in dynamic environments based on Factor Graphs and the Max-Sum algorithm, considering asynchronous variable reassignments and distributed message-passing among agents. Motivated by the challenging domain of lane-free traffic where automated vehicles can communicate and coordinate as agents, we propose a more realistic communication framework for Factor Graph formulations that satisfies the above-mentioned restrictions, along with Conditional Max-Sum: an extension of Max-Sum with a revised message-passing process that is better suited for asynchronous settings. The overall application in lane-free traffic can be viewed as a hybrid system where the Factor Graph formulation undertakes the strategic decision making of vehicles, that of desired lateral alignment in a coordinated manner; and acts on top of a rule-based method we devise that provides a structured representation of the lane-free environment for the factors, while also handling the underlying control of vehicles regarding core operations and safety. Our experimental evaluation showcases the capabilities of the proposed framework in problems with intense coordination needs when compared to a domain-specific baseline without communication, and an increased adeptness of Conditional Max-Sum with respect to the standard algorithm.

cs.MA↗

arXiv2023

A Novel Multiagent Flexibility Aggregation Framework

The increasing number of Distributed Energy Resources (DERs) in the emerging Smart Grid, has created an imminent need for intelligent multiagent frameworks able to utilize these assets efficiently. In this paper, we propose a novel DER aggregation framework, encompassing a multiagent architecture and various types of mechanisms for the effective management and efficient integration of DERs in the Grid. One critical component of our architecture is the Local Flexibility Estimators (LFEs) agents, which are key for offloading the Aggregator from serious or resource-intensive responsibilities -- such as addressing privacy concerns and predicting the accuracy of DER statements regarding their offered demand response services. The proposed framework allows the formation of efficient LFE cooperatives. To this end, we developed and deployed a variety of cooperative member selection mechanisms, including (a) scoring rules, and (b) (deep) reinforcement learning. We use data from the well-known PowerTAC simulator to systematically evaluate our framework. Our experiments verify its effectiveness for incorporating heterogeneous DERs into the Grid in an efficient manner. In particular, when using the well-known probabilistic prediction accuracy-incentivizing CRPS scoring rule as a selection mechanism, our framework results in increased average payments for participants, when compared with traditional commercial aggregators.

cs.AI↗

arXiv2021

Optimising Long-Term Outcomes using Real-World Fluent Objectives: An Application to Football

In this paper, we present a novel approach for optimising long-term tactical and strategic decision-making in football (soccer) by encapsulating events in a league environment across a given time frame. We model the teams' objectives for a season and track how these evolve as games unfold to give a fluent objective that can aid in decision-making games. We develop Markov chain Monte Carlo and deep learning-based algorithms that make use of the fluent objectives in order to learn from prior games and other games in the environment and increase the teams' long-term performance. Simulations of our approach using real-world datasets from 760 matches shows that by using optimised tactics with our fluent objective and prior games, we can on average increase teams mean expected finishing distribution in the league by up to 35.6%.

cs.AI↗

arXiv2020

Optimising Game Tactics for Football

In this paper we present a novel approach to optimise tactical and strategic decision making in football (soccer). We model the game of football as a multi-stage game which is made up from a Bayesian game to model the pre-match decisions and a stochastic game to model the in-match state transitions and decisions. Using this formulation, we propose a method to predict the probability of game outcomes and the payoffs of team actions. Building upon this, we develop algorithms to optimise team formation and in-game tactics with different objectives. Empirical evaluation of our approach on real-world datasets from 760 matches shows that by using optimised tactics from our Bayesian and stochastic games, we can increase a team chances of winning by up to 16.1\% and 3.4\% respectively.

cs.AI↗

arXiv2018

Overlapping Coalition Formation via Probabilistic Topic Modeling

Research in cooperative games often assumes that agents know the coalitional values with certainty, and that they can belong to one coalition only. By contrast, this work assumes that the value of a coalition is based on an underlying collaboration structure emerging due to existing but unknown relations among the agents; and that agents can form overlapping coalitions. Specifically, we first propose Relational Rules, a novel representation scheme for cooperative games with overlapping coalitions, which encodes the aforementioned relations, and which extends the well-known MC-nets representation to this setting. We then present a novel decision-making method for decentralized overlapping coalition formation, which exploits probabilistic topic modeling, and in particular, online Latent Dirichlet Allocation. By interpreting formed coalitions as documents, agents can effectively learn topics that correspond to profitable collaboration structures.

cs.GT↗

arXiv2014

Cooperative Games with Overlapping Coalitions: Charting the Tractability Frontier

In many multiagent scenarios, agents distribute resources, such as time or energy, among several tasks. Having completed their tasks and generated profits, task payoffs must be divided among the agents in some reasonable manner. Cooperative games with overlapping coalitions (OCF games) are a recent framework proposed by Chalkiadakis et al. (2010), generalizing classic cooperative games to the case where agents may belong to more than one coalition. Having formed overlapping coalitions and divided profits, some agents may feel dissatisfied with their share of the profits, and would like to deviate from the given outcome. However, deviation in OCF games is a complicated matter: agents may decide to withdraw only some of their weight from some of the coalitions they belong to; that is, even after deviation, it is possible that agents will still be involved in tasks with non-deviators. This means that the desirability of a deviation, and the stability of formed coalitions, is to a great extent determined by the reaction of non-deviators. In this work, we explore algorithmic aspects of OCF games, focusing on the core in OCF games. We study the problem of deciding if the core of an OCF game is not empty, and whether a core payoff division can be found in polynomial time; moreover, we identify conditions that ensure that the problem admits polynomial time algorithms. Finally, we introduce and study a natural class of OCF games, Linear Bottleneck Games. Interestingly, we show that such games always have a non-empty core, even assuming a highly lenient reaction to deviations.

cs.GT↗

arXiv2014

Cooperative Games with Overlapping Coalitions

In the usual models of cooperative game theory, the outcome of a coalition formation process is either the grand coalition or a coalition structure that consists of disjoint coalitions. However, in many domains where coalitions are associated with tasks, an agent may be involved in executing more than one task, and thus may distribute his resources among several coalitions. To tackle such scenarios, we introduce a model for cooperative games with overlapping coalitions--or overlapping coalition formation (OCF) games. We then explore the issue of stability in this setting. In particular, we introduce a notion of the core, which generalizes the corresponding notion in the traditional (non-overlapping) scenario. Then, under some quite general conditions, we characterize the elements of the core, and show that any element of the core maximizes the social welfare. We also introduce a concept of balancedness for overlapping coalitional games, and use it to characterize coalition structures that can be extended to elements of the core. Finally, we generalize the notion of convexity to our setting, and show that under some natural assumptions convex games have a non-empty core. Moreover, we introduce two alternative notions of stability in OCF that allow a wider range of deviations, and explore the relationships among the corresponding definitions of the core, as well as the classic (non-overlapping) core and the Aubin core. We illustrate the general properties of the three cores, and also study them from a computational perspective, thus obtaining additional insights into their fundamental structure.

cs.GT↗