arXiv subjects

Eduardo Alonso

Publications and source records attributed to Eduardo Alonso.

18 recordsLinked to original sources

arXiv2026

Groupoid-Based Internal State Representations for Reinforcement Learning with Local Symmetries

Symmetries play a central role in reducing the complexity of reinforcement learning problems, yet most existing approaches rely on fixed group actions or predefined state abstractions. Classical reinforcement learning algorithms typically assume a globally structured Markov decision process with uniformly applicable actions and transitions, an assumption that limits their ability to exploit modularity and local, context-dependent regularities present in many realistic environments. We propose a reinforcement learning framework using groupoids to capture local, state-dependent symmetries and support the dy- namic discovery of equivalence structures during interaction. The agent maintains orbit representatives together with transporters that map raw states to canonical forms, enabling learning and decision-making to be performed in a symmetry-reduced space while preserving local distinctions. Empirical results demonstrate that the proposed groupoid-based approach improves sample efficiency and convergence in dense and large-scale environments exhibiting strong partial symmetries, yielding substantial performance gains over standard Q-learning. These findings show that dynamically exploiting local symmetry provides a practical and mathematically principled route to scalable and generalisable reinforcement learning.

cs.LG↗

arXiv2026

A representational framework for learning and encoding structurally enriched trajectories in complex agent environments

The ability of artificial intelligence agents to make optimal decisions and generalise them to different domains and tasks is compromised in complex scenarios. One way to address this issue has focused on learning efficient representations of the world and on how the actions of agents affect them in state-action transitions. Whereas such representations are procedurally efficient, they lack structural richness. To address this problem, we propose to enhance the agent's ontology and extend the traditional conceptualisation of trajectories to provide a more nuanced view of task execution. Structurally Enriched Trajectories (SETs) extend the encoding of sequences of states and their transitions by incorporating hierarchical relations between objects, interactions, and affordances. SETs are built as multi-level graphs, providing a detailed representation of the agent dynamics and a transferable functional abstraction of the task. SETs are integrated into an architecture, Structurally Enriched Trajectory Learning and Encoding (SETLE), that employs a heterogeneous graph-based memory structure of multi-level relational dependencies essential for generalisation. We demonstrate that SETLE can support downstream tasks, enabling agents to recognise task relevant structural patterns across CREATE and MiniGrid environments. Finally, we integrate SETLE with reinforcement learning and show measurable improvements in downstream performance, including breakthrough success rates in complex, sparse-reward tasks.

cs.AI↗

arXiv2025

Algebras of actions in an agent's representations of the world

In this paper, we propose a framework to extract the algebra of the transformations of worlds from the perspective of an agent. As a starting point, we use our framework to reproduce the symmetry-based representations from the symmetry-based disentangled representation learning (SBDRL) formalism proposed by [1]; only the algebra of transformations of worlds that form groups can be described using symmetry-based representations. We then study the algebras of the transformations of worlds with features that occur in simple reinforcement learning scenarios. Using computational methods, that we developed, we extract the algebras of the transformations of these worlds and classify them according to their properties. Finally, we generalise two important results of SBDRL - the equivariance condition and the disentangling definition - from only working with symmetry-based representations to working with representations capturing the transformation properties of worlds with transformations for any algebra. Finally, we combine our generalised equivariance condition and our generalised disentangling definition to show that disentangled sub-algebras can each have their own individual equivariance conditions, which can be treated independently.

cs.AI↗

arXiv2025

Transformer World Model for Sample Efficient Multi-Agent Reinforcement Learning

We present the Multi-Agent Transformer World Model (MATWM), a novel transformer-based world model designed for multi-agent reinforcement learning in both vector- and image-based environments. MATWM combines a decentralized imagination framework with a semi-centralized critic and a teammate prediction module, enabling agents to model and anticipate the behavior of others under partial observability. To address non-stationarity, we incorporate a prioritized replay mechanism that trains the world model on recent experiences, allowing it to adapt to agents' evolving policies. We evaluated MATWM on a broad suite of benchmarks, including the StarCraft Multi-Agent Challenge, PettingZoo, and MeltingPot. MATWM achieves state-of-the-art performance, outperforming both model-free and prior world model approaches, while demonstrating strong sample efficiency, achieving near-optimal performance in as few as 50K environment interactions. Ablation studies confirm the impact of each component, with substantial gains in coordination-heavy tasks.

cs.LG↗

arXiv2024

Mutation-Bias Learning in Games

We present two variants of a multi-agent reinforcement learning algorithm based on evolutionary game theoretic considerations. The intentional simplicity of one variant enables us to prove results on its relationship to a system of ordinary differential equations of replicator-mutator dynamics type, allowing us to present proofs on the algorithm's convergence conditions in various settings via its ODE counterpart. The more complicated variant enables comparisons to Q-learning based algorithms. We compare both variants experimentally to WoLF-PHC and frequency-adjusted Q-learning on a range of settings, illustrating cases of increasing dimensionality where our variants preserve convergence in contrast to more complicated algorithms. The availability of analytic results provides a degree of transferability of results as compared to purely empirical case studies, illustrating the general utility of a dynamical systems perspective on multi-agent reinforcement learning when addressing questions of convergence and reliable generalisation.

cs.LG↗

arXiv2023

DiT-Head: High-Resolution Talking Head Synthesis using Diffusion Transformers

We propose a novel talking head synthesis pipeline called "DiT-Head", which is based on diffusion transformers and uses audio as a condition to drive the denoising process of a diffusion model. Our method is scalable and can generalise to multiple identities while producing high-quality results. We train and evaluate our proposed approach and compare it against existing methods of talking head synthesis. We show that our model can compete with these methods in terms of visual quality and lip-sync accuracy. Our results highlight the potential of our proposed approach to be used for a wide range of applications, including virtual assistants, entertainment, and education. For a video demonstration of the results and our user study, please refer to our supplementary material.

cs.AI↗

arXiv2023

Cognitively Inspired Components for Social Conversational Agents

Current conversational agents (CA) have seen improvement in conversational quality in recent years due to the influence of large language models (LLMs) like GPT3. However, two key categories of problem remain. Firstly there are the unique technical problems resulting from the approach taken in creating the CA, such as scope with retrieval agents and the often nonsensical answers of former generative agents. Secondly, humans perceive CAs as social actors, and as a result expect the CA to adhere to social convention. Failure on the part of the CA in this respect can lead to a poor interaction and even the perception of threat by the user. As such, this paper presents a survey highlighting a potential solution to both categories of problem through the introduction of cognitively inspired additions to the CA. Through computational facsimiles of semantic and episodic memory, emotion, working memory, and the ability to learn, it is possible to address both the technical and social problems encountered by CAs.

cs.CL↗

arXiv2023

AIGenC: An AI generalisation model via creativity

Inspired by cognitive theories of creativity, this paper introduces a computational model (AIGenC) that lays down the necessary components to enable artificial agents to learn, use and generate transferable representations. Unlike machine representation learning, which relies exclusively on raw sensory data, biological representations incorporate relational and associative information that embeds rich and structured concept spaces. The AIGenC model poses a hierarchical graph architecture with various levels and types of representations procured by different components. The first component, Concept Processing, extracts objects and affordances from sensory input and encodes them into a concept space. The resulting representations are stored in a dual memory system and enriched with goal-directed and temporal information acquired through reinforcement learning, creating a higher-level of abstraction. Two additional components work in parallel to detect and recover relevant concepts and create new ones, respectively, in a process akin to cognitive Reflective Reasoning and Blending. The Reflective Reasoning unit detects and recovers from memory concepts relevant to the task by means of a matching process that calculates a similarity value between the current state and memory graph structures. Once the matching interaction ends, rewards and temporal information are added to the graph, building further abstractions. If the reflective reasoning processing fails to offer a suitable solution, a blending operation comes into place, creating new concepts by combining past information. We discuss the model's capability to yield better out-of-distribution generalisation in artificial agents, thus advancing toward Artificial General Intelligence.

cs.AI↗

arXiv2023

Switchable Lightweight Anti-symmetric Processing (SLAP) with CNN Outspeeds Data Augmentation by Smaller Sample -- Application in Gomoku Reinforcement Learning

To replace data augmentation, this paper proposed a method called SLAP to intensify experience to speed up machine learning and reduce the sample size. SLAP is a model-independent protocol/function to produce the same output given different transformation variants. SLAP improved the convergence speed of convolutional neural network learning by 83% in the experiments with Gomoku game states, with only one eighth of the sample size compared with data augmentation. In reinforcement learning for Gomoku, using AlphaGo Zero/AlphaZero algorithm with data augmentation as baseline, SLAP reduced the number of training samples by a factor of 8 and achieved similar winning rate against the same evaluator, but it was not yet evident that it could speed up reinforcement learning. The benefits should at least apply to domains that are invariant to symmetry or certain transformations. As future work, SLAP may aid more explainable learning and transfer learning for domains that are not invariant to symmetry, as a small step towards artificial general intelligence.

cs.LG↗

arXiv2022

Efficient entity-based reinforcement learning

Recent deep reinforcement learning (DRL) successes rely on end-to-end learning from fixed-size observational inputs (e.g. image, state-variables). However, many challenging and interesting problems in decision making involve observations or intermediary representations which are best described as a set of entities: either the image-based approach would miss small but important details in the observations (e.g. ojects on a radar, vehicles on satellite images, etc.), the number of sensed objects is not fixed (e.g. robotic manipulation), or the problem simply cannot be represented in a meaningful way as an image (e.g. power grid control, or logistics). This type of structured representations is not directly compatible with current DRL architectures, however, there has been an increase in machine learning techniques directly targeting structured information, potentially addressing this issue. We propose to combine recent advances in set representations with slot attention and graph neural networks to process structured data, broadening the range of applications of DRL algorithms. This approach allows to address entity-based problems in an efficient and scalable way. We show that it can improve training time and robustness significantly, and demonstrate their potential to handle structured as well as purely visual domains, on multiple environments from the Atari Learning Environment and Simple Playgrounds.

cs.LG↗

arXiv2021

Logo Generation Using Regional Features: A Faster R-CNN Approach to Generative Adversarial Networks

In this paper we introduce Local Logo Generative Adversarial Network (LL-GAN) that uses regional features extracted from Faster R-CNN for logo generation. We demonstrate the strength of this approach by training the framework on a small style-rich dataset of real heavy metal logos to generate new ones. LL-GAN achieves Inception Score of 5.29 and Frechet Inception Distance of 223.94, improving on state-of-the-art models StyleGAN2 and Self-Attention GAN.

cs.CV↗

arXiv2020

Deep Multi-Agent Reinforcement Learning for Cost Efficient Distributed Load Frequency Control

The rise of microgrid-based architectures is heavily modifying the energy control landscape in distribution systems making distributed control mechanisms necessary to ensure reliable power system operations. In this paper, we propose the use of Reinforcement Learning techniques to implement load frequency control without requiring a central authority. To this end, we approximate the optimal solution of the primary, secondary, and tertiary control with the use of the Multi- Agent Deep Deterministic Policy Gradient (MADDPG) algorithm. Generation units are characterised as agents that learn how to maximise their long-term performance by acting and interacting with the environment to balance generation and load in a cost efficient way. Network effects are also modelled in our framework for the restoration of frequency to the nominal value. We validate our Reinforcement Learning methodology through numerical results and show that it can be used to implement the load frequency control in a distributed and cost efficient way.

eess.SY↗

arXiv2020

Gaussian Process Regression for Probabilistic Short-term Solar Output Forecast

With increasing concerns of climate change, renewable resources such as photovoltaic (PV) have gained popularity as a means of energy generation. The smooth integration of such resources in power system operations is enabled by accurate forecasting mechanisms that address their inherent intermittency and variability. This paper proposes a probabilistic framework to predict short-term PV output taking into account the uncertainty of weather. To this end, we make use of datasets that comprise of power output and meteorological data such as irradiance, temperature, zenith, and azimuth. First, we categorise the data into four groups based on solar output and time by using k-means clustering. Next, a correlation study is performed to choose the weather features which affect solar output to a greater extent. Finally, we determine a function that relates the aforementioned selected features with solar output by using Gaussian Process Regression and Matern 5/2 as a kernel function. We validate our method with five solar generation plants in different locations and compare the results with existing methodologies. More specifically, in order to test the proposed model, two different methods are used: (i) 5-fold cross-validation; and (ii) holding out 30 random days as test data. To confirm the model accuracy, we apply our framework 30 independent times on each of the four clusters. The average error follows a normal distribution, and with 95% confidence level, it takes values between -1.6% to 1.4%.

stat.AP↗

arXiv2019

The Stabilisation of Equilibria in Evolutionary Game Dynamics through Mutation: Mutation Limits in Evolutionary Games

The multi-population replicator dynamics (RD) can be considered a dynamic approach to the study of multi-player games, where it was shown to be related to Cross' learning, as well as of systems of coevolving populations. However, not all of its equilibria are Nash equilibria (NE) of the underlying game, and neither convergence to an NE nor convergence in general are guaranteed. Although interior equilibria are guaranteed to be NE, no interior equilibrium can be asymptotically stable in the multi-population RD, resulting, e.g., in cyclic orbits around a single interior NE. We introduce a new notion of equilibria of RD, called mutation limits, which is based on the inclusion of a naturally arising, simple form of mutation, but is invariant under the specific choice of mutation parameters. We prove the existence of such mutation limits for a large range of games, and consider a subclass of particular interest, that of attracting mutation limits. Attracting mutation limits are approximated by asymptotically stable equilibria of the (mutation-)perturbed RD, and hence, offer an approximate dynamic solution of the underlying game, especially if the original dynamic has no asymptotically stable equilibria. In this sense, mutation stabilises the system in certain cases and makes attracting mutation limits near-attainable. Furthermore, the relevance of attracting mutation limits as a game theoretic equilibrium concept is emphasised by a similarity of (mutation-)perturbed RD to the Q-learning algorithm in the context of multi-agent reinforcement learning. In contrast to the guaranteed existence of mutation limits, attracting mutation limits do not exist in all games, raising the question of their characterization.

q-bio.PE↗

arXiv2018

Generating Magnetic Resonance Spectroscopy Imaging Data of Brain Tumours from Linear, Non-Linear and Deep Learning Models

Magnetic Resonance Spectroscopy (MRS) provides valuable information to help with the identification and understanding of brain tumors, yet MRS is not a widely available medical imaging modality. Aiming to counter this issue, this research draws on the advancements in machine learning techniques in other fields for the generation of artificial data. The generated methods were tested through the evaluation of their output against that of a real-world labelled MRS brain tumor data-set. Furthermore the resultant output from the generative techniques were each used to train separate traditional classifiers which were tested on a subset of the real MRS brain tumor dataset. The results suggest that there exist methods capable of producing accurate, ground truth based MRS voxels. These findings indicate that through generative techniques, large datasets can be made available for training deep, learning models for the use in brain tumor diagnosis.

cs.CV↗

arXiv2018

Towards Symbolic Reinforcement Learning with Common Sense

Deep Reinforcement Learning (deep RL) has made several breakthroughs in recent years in applications ranging from complex control tasks in unmanned vehicles to game playing. Despite their success, deep RL still lacks several important capacities of human intelligence, such as transfer learning, abstraction and interpretability. Deep Symbolic Reinforcement Learning (DSRL) seeks to incorporate such capacities to deep Q-networks (DQN) by learning a relevant symbolic representation prior to using Q-learning. In this paper, we propose a novel extension of DSRL, which we call Symbolic Reinforcement Learning with Common Sense (SRL+CS), offering a better balance between generalization and specialization, inspired by principles of common sense when assigning rewards and aggregating Q-values. Experiments reported in this paper show that SRL+CS learns consistently faster than Q-learning and DSRL, achieving also a higher accuracy. In the hardest case, where agents were trained in a deterministic environment and tested in a random environment, SRL+CS achieves nearly 100% average accuracy compared to DSRL's 70% and DQN's 50% accuracy. To the best of our knowledge, this is the first case of near perfect zero-shot transfer learning using Reinforcement Learning.

cs.LG↗

arXiv2012

The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation

This paper gives specific divergence examples of value-iteration for several major Reinforcement Learning and Adaptive Dynamic Programming algorithms, when using a function approximator for the value function. These divergence examples differ from previous divergence examples in the literature, in that they are applicable for a greedy policy, i.e. in a "value iteration" scenario. Perhaps surprisingly, with a greedy policy, it is also possible to get divergence for the algorithms TD(1) and Sarsa(1). In addition to these divergences, we also achieve divergence for the Adaptive Dynamic Programming algorithms HDP, DHP and GDHP.

cs.LG↗

arXiv2011

The Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning

In this theoretical paper we are concerned with the problem of learning a value function by a smooth general function approximator, to solve a deterministic episodic control problem in a large continuous state space. It is shown that learning the gradient of the value-function at every point along a trajectory generated by a greedy policy is a sufficient condition for the trajectory to be locally extremal, and often locally optimal, and we argue that this brings greater efficiency to value-function learning. This contrasts to traditional value-function learning in which the value-function must be learnt over the whole of state space. It is also proven that policy-gradient learning applied to a greedy policy on a value-function produces a weight update equivalent to a value-gradient weight update, which provides a surprising connection between these two alternative paradigms of reinforcement learning, and a convergence proof for control problems with a value function represented by a general smooth function approximator.

cs.LG↗