State-of-the-art imitation learning from observation methods (ILfO) have recently made significant progress, but they still have some limitations: they need action-based supervised optimisation, assume that states have a single optimal action, and tend to apply teacher actions without full consideration of the actual environment state. While the truth may be out there in observed trajectories, existing methods struggle to extract it without supervision. In this work, we propose Unsupervised Imitation Learning from Observation (UfO) that addresses all of these limitations. UfO learns a policy through a two-stage process, in which the agent first obtains an approximation of the teacher's true actions in the observed state transitions, and then refines the learned policy further by adjusting agent trajectories to closely align them with the teacher's. Experiments we conducted in five widely used environments show that UfO not only outperforms the teacher and all other ILfO methods but also displays the smallest standard deviation. This reduction in standard deviation indicates better generalisation in unseen scenarios.

Online goal recognition in continuous domains poses two central challenges: efficiently encoding large trajectories and effectively comparing them. Recent work addresses these challenges by using custom state-space representations and metrics to compare observations against hypotheses. However, these approaches often overlook well-established encoding techniques used in other domains that offer substantial advantages. This paper introduces a novel method for online goal recognition that leverages path signatures, a compact, expressive representation of rough path theory that captures key semantic features of trajectories in an efficient way, enabling more meaningful comparisons between them. Experiments show that our method consistently outperforms the state of the art in predictive accuracy and online planning efficiency, while remaining competitive offline.

Reinforcement Learning (RL) policies often degrade in unfamiliar environments because they lack explicit deliberation. We propose Plan, Align, Commit, Think (PACT), a hybrid architecture that combines a fast, reactive RL policy with a slow, deliberative Small Language Model (SLM) planner. PACT invokes the SLM asynchronously to generate and validate candidate action plans. Once a plan is verified through simulation as safe, feasible, and complete, it is executed directly, bypassing the RL policy without retraining or modifying it. Evaluated on three FrozenLake configurations of increasing difficulty, PACT outperforms all baselines while relying on a 2B-parameter SLM backbone, suggesting that deliberative planning and reactive execution are more powerful in concert than either is alone in these settings.

Reinforcement learning (RL) agents often struggle with out-of-distribution (OOD) scenarios, leading to high uncertainty and random behavior. While language models (LMs) contain valuable world knowledge, larger ones incur high computational costs, hindering real-time use, and exhibit limitations in autonomous planning. We introduce Adaptive Safety through Knowledge (ASK), which combines smaller LMs with trained RL policies to enhance OOD generalization without retraining. ASK employs Monte Carlo Dropout to assess uncertainty and queries the LM for action suggestions only when uncertainty exceeds a set threshold. This selective use preserves the efficiency of existing policies while leveraging the language model's reasoning in uncertain situations. In experiments on the FrozenLake environment, ASK shows no improvement in-domain, but demonstrates robust navigation in transfer tasks, achieving a reward of 0.95. Our findings indicate that effective neuro-symbolic integration requires careful orchestration rather than simple combination, highlighting the need for sufficient model scale and effective hybridization mechanisms for successful OOD generalization.

Large language models have recently reached near-parity with classical planners on well-known planning domains, yet this competence relies on world-knowledge exploitation rather than genuine symbolic reasoning. Goal recognition is a complementary abductive task structurally better suited to LLM strengths: it consists of evaluating consistency with world knowledge rather than generating novel action sequences. This paper provides the first systematic zero-shot evaluation of frontier LLMs as goal recognisers on key classical PDDL benchmarks. Our results show that LLM competence on goal recognition is uneven: some models scale with evidence and approach landmark-based accuracy at full observations, while others remain anchored to world-knowledge priors regardless of how much evidence accumulates. Qualitative analysis of model reasoning traces reveals that this divergence reflects a fundamental difference in evidence integration rather than domain familiarity. These findings position goal recognition as a principled benchmark for the foundational planning knowledge of LLMs.

Reinforcement learning agents operating under partial observability must act on incomplete information, making them natural candidates for guidance from small language models (SLMs) that carry broad reasoning priors. Yet integrating SLM guidance into this setting has proven difficult: across all test environments, vanilla uncertainty-gated approaches achieve an overwrite rate at or near zero, meaning the SLM almost never contributes an independent action. We trace this failure to the bare egocentric prompt, which provides insufficient context for genuine reasoning, and identify it as a context problem rather than a capacity problem. We propose ASK+, which supplies the SLM with trajectory-aware context (a partially revealed map, visited positions, and action history) and structured chain-of-thought reasoning, converting it from a passive redundancy check into a more informative consultant that occasionally corrects the policy. We further establish that the predictive entropy signal used for selective querying measures action uncertainty rather than state uncertainty and remains informative in POMDPs, making uncertainty-gated assistance viable beyond fully observable settings. The stateful prompt drives substantial gains: on DoorKey, where vanilla ASK matches PPO (both 89

Imitation learning stands at a crossroads: despite decades of progress, current imitation learning agents remain sophisticated memorisation machines, excelling at replay but failing when contexts shift or goals evolve. This paper argues that this failure is not technical but foundational: imitation learning has been optimised for the wrong objective. We propose a research agenda that redefines success from perfect replay to compositional adaptability. Such adaptability hinges on learning behavioural primitives once and recombining them through novel contexts without retraining. We establish metrics for compositional generalisation, propose hybrid architectures, and outline interdisciplinary research directions drawing on cognitive science and cultural evolution. Agents that embed adaptability at the core of imitation learning thus have an essential capability for operating in an open-ended world.

Despite being responsible for state-of-the-art results in several computer vision and natural language processing tasks, neural networks have faced harsh criticism due to some of their current shortcomings. One of them is that neural networks are correlation machines prone to model biases within the data instead of focusing on actual useful causal relationships. This problem is particularly serious in application domains affected by aspects such as race, gender, and age. To prevent models from incurring unfair decision-making, the AI community has concentrated efforts on correcting algorithmic biases, giving rise to the research area now widely known as fairness in AI . In this survey paper, we provide an in-depth overview of the main debiasing methods for fairness-aware neural networks in the context of vision and language research. We propose a novel taxonomy that builds upon previous proposals but is tailored for deep learning research to better organize the literature on debiasing methods for fairness. We review all important neural-based methods and evaluation metrics while discussing the current challenges, trends, and important future work directions for the interested researcher and practitioner.

Imitation learning benchmarks often lack sufficient variation between training and evaluation, limiting meaningful generalisation assessment. We introduce Labyrinth, a benchmarking environment designed to test generalisation with precise control over structure, start and goal positions, and task complexity. It enables verifiably distinct training, evaluation, and test settings. Labyrinth provides a discrete, fully observable state space and known optimal actions, supporting interpretability and fine-grained evaluation. Its flexible setup allows targeted testing of generalisation factors and includes variants like partial observability, key-and-door tasks, and ice-floor hazards. By enabling controlled, reproducible experiments, Labyrinth advances the evaluation of generalisation in imitation learning and provides a valuable tool for developing more robust agents.

Some imitation learning methods combine behavioural cloning with self-supervision to infer actions from state pairs. However, most rely on a large number of expert trajectories to increase generalisation and human intervention to capture key aspects of the problem, such as domain constraints. In this paper, we propose Continuous Imitation Learning from Observation (CILO), a new method augmenting imitation learning with two important features: (i) exploration, allowing for more diverse state transitions, requiring less expert trajectories and resulting in fewer training iterations; and (ii) path signatures, allowing for automatic encoding of constraints, through the creation of non-parametric representations of agents and expert trajectories. We compared CILO with a baseline and two leading imitation learning methods in five environments. It had the best overall performance of all methods in all environments, outperforming the expert in two of them.

Imitation learning is an approach in which an agent learns how to execute a task by trying to mimic how one or more teachers perform it. This learning approach offers a compromise between the time it takes to learn a new task and the effort needed to collect teacher samples for the agent. It achieves this by balancing learning from the teacher, who has some information on how to perform the task, and deviating from their examples when necessary, such as states not present in the teacher samples. Consequently, the field of imitation learning has received much attention from researchers in recent years, resulting in many new methods and applications. However, with this increase in published work and past surveys focusing mainly on methodology, a lack of standardisation became more prominent in the field. This non-standardisation is evident in the use of environments, which appear in no more than two works, and evaluation processes, such as qualitative analysis, that have become rare in current literature. In this survey, we systematically review current imitation learning literature and present our findings by (i) classifying imitation learning techniques, environments and metrics by introducing novel taxonomies; (ii) reflecting on main problems from the literature; and (iii) presenting challenges and future directions for researchers.

Imitation learning field requires expert data to train agents in a task. Most often, this learning approach suffers from the absence of available data, which results in techniques being tested on its dataset. Creating datasets is a cumbersome process requiring researchers to train expert agents from scratch, record their interactions and test each benchmark method with newly created data. Moreover, creating new datasets for each new technique results in a lack of consistency in the evaluation process since each dataset can drastically vary in state and action distribution. In response, this work aims to address these issues by creating Imitation Learning Datasets, a toolkit that allows for: (i) curated expert policies with multithreaded support for faster dataset creation; (ii) readily available datasets and techniques with precise measurements; and (iii) sharing implementations of common imitation learning techniques. Demonstration link: https://nathangavenski.github.io/#/il-datasets-video

Objective:To determinate the accuracy of computed tomography (CT) imaging assessed by deep neural networks for predicting the need for mechanical ventilation (MV) in patients hospitalized with severe acute respiratory syndrome due to coronavirus disease 2019 (COVID-19).Materials and Methods:This was a retrospective cohort study carried out at two hospitals in Brazil. We included CT scans from patients who were hospitalized due to severe acute respiratory syndrome and had COVID-19 confirmed by reverse transcription-polymerase chain reaction (RT-PCR). The training set consisted of chest CT examinations from 823 patients with COVID-19, of whom 93 required MV during hospitalization. We developed an artificial intelligence (AI) model based on convolutional neural networks. The performance of the AI model was evaluated by calculating its accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve.Results:For predicting the need for MV, the AI model had a sensitivity of 0.417 and a specificity of 0.860. The corresponding area under the ROC curve for the test set was 0.68.Conclusion:The high specificity of our AI model makes it able to reliably predict which patients will and will not need invasive ventilation. That makes this approach ideal for identifying high-risk patients and predicting the minimum number of ventilators and critical care beds that will be required.

Behavioural cloning is an imitation learning technique that teaches an agent how to behave via expert demonstrations. Recent approaches use self-supervision of fully-observable unlabelled snapshots of the states to decode state pairs into actions. However, the iterative learning scheme employed by these techniques is prone to get trapped into bad local minima. Previous work uses goal-aware strategies to solve this issue. However, this requires manual intervention to verify whether an agent has reached its goal. We address this limitation by incorporating a discriminator into the original framework, offering two key advantages and directly solving a learning problem previous work had. First, it disposes of the manual intervention requirement. Second, it helps in learning by guiding function approximation based on the state transition of the expert's trajectories. Third, the discriminator solves a learning issue commonly present in the policy model, which is to sometimes perform a 'no action' within the environment until the agent finally halts.

Despite the success of neural architectures for Visual Question Answering (VQA), several recent studies have shown that VQA models are mostly driven by superficial correlations that are learned by exploiting undesired priors within training datasets. They often lack sufficient image grounding or tend to overly-rely on textual information, failing to capture knowledge from the images. This affects their generalization to test sets with slight changes in the distribution of facts. To address such an issue, some bias mitigation methods have relied on new training procedures that are capable of synthesizing counterfactual samples by masking critical objects within the images, and words within the questions, while also changing the corresponding ground truth. We propose a novel model-agnostic counterfactual training procedure, namely Efficient Counterfactual Debiasing (ECD), in which we introduce a new negative answer-assignment mechanism that exploits the probability distribution of the answers based on their frequencies, as well as an improved counterfactual sample synthesizer. Our experiments demonstrate that ECD is a simple, computationally-efficient counterfactual sample-synthesizer training procedure that establishes itself as the new state of the art for unbiased VQA.

Despite being responsible for state-of-the-art results in several computer vision and natural language processing tasks, neural networks have faced harsh criticism due to some of their current shortcomings. One of them is that neural networks are correlation machines prone to model biases within the data instead of focusing on actual useful causal relationships. This problem is particularly serious in application domains affected by aspects such as race, gender, and age. To prevent models from incurring on unfair decision-making, the AI community has concentrated efforts in correcting algorithmic biases, giving rise to the research area now widely known as fairness in AI. In this survey paper, we provide an in-depth overview of the main debiasing methods for fairness-aware neural networks in the context of vision and language research. We propose a novel taxonomy to better organize the literature on debiasing methods for fairness, and we discuss the current challenges, trends, and important future work directions for the interested researcher and practitioner.

Imitation Learning (IL) algorithms try to mimic expert behavior in order to be capable of performing specific tasks, but it remains unclear what those strategies could achieve when learning from sub-optimal data (faulty experts). Studying how Imitation Learning approaches learn when dealing with different degrees of quality from the observations can benefit tasks such as optimizing data collection, producing interpretable models, reducing bias when using sub-optimal experts, and more. Therefore, in this work we provide extensive experiments to verify how different Imitation Learning agents perform under various degrees of expert optimality. We experiment with four IL algorithms, three of them that learn self-supervisedly and one that uses the ground-truth labels (BC) in four different environments (tasks), and we compare them using optimal and sub-optimal experts. For assessing the performance of each agent, we compute two metrics: Performance and Average Episodic Reward. Our experiments show that IL approaches that learn self-supervisedly are relatively resilient to sub-optimal experts, which is not the case of the supervised approach. We also observe that suboptimal experts are sometimes beneficial since they seem to act as a kind of regularization method, preventing models from data overfitting. You can replicate our experiments by using the code in our GitHub (https://github.com/NathanGavenski/How-resilient-IL-methods-are).

Imitation from observation is a computational technique that teaches an agent on how to mimic the behavior of an expert by observing only the sequence of states from the expert demonstrations. Recent approaches learn the inverse dynamics of the environment and an imitation policy by interleaving epochs of both models while changing the demonstration data. However, such approaches often get stuck into sub-optimal solutions that are distant from the expert, limiting their imitation effectiveness. We address this problem with a novel approach that overcomes the problem of reaching bad local minima by exploring: (i) a self-attention mechanism that better captures global features of the states; and (ii) a sampling strategy that regulates the observations that are used for learning. We show empirically that our approach outperforms the state-of-the-art approaches in four different environments by a large margin.

Behavioral cloning is an imitation learning technique that teaches an agent how to behave through expert demonstrations. Recent approaches use self-supervision of fully-observable unlabeled snapshots of the states to decode state-pairs into actions. However, the iterative learning scheme from these techniques are prone to getting stuck into bad local minima. We address these limitations incorporating a two-phase model into the original framework, which learns from unlabeled observations via exploration, substantially improving traditional behavioral cloning by exploiting (i) a sampling mechanism to prevent bad local minima, (ii) a sampling mechanism to improve exploration, and (iii) self-attention modules to capture global features. The resulting technique outperforms the previous state-of-the-art in four different environments by a large margin.

Recently, learning-based approaches for 3D reconstruction from 2D images have gained popularity due to its modern applications, e.g., 3D printers, autonomous robots, self-driving cars, virtual reality, and augmented reality. The computer vision community has applied a great effort in developing functions to reconstruct the full 3D geometry of objects and scenes. However, to extract image features, they rely on convolutional neural networks, which are ineffective in capturing long-range dependencies. In this paper, we propose to substantially improve Occupancy Networks, a state-of-the-art method for 3D object reconstruction. For such we apply the concept of self-attention within the network's encoder in order to leverage complementary input features rather than those based on local regions, helping the encoder to extract global information. With our approach, we were capable of improving the original work in 5.05% of mesh IoU, 0.83% of Normal Consistency, and more than 10x the Chamfer-L1 distance. We also perform a qualitative study that shows that our approach was able to generate much more consistent meshes, confirming its increased generalization power over the current state-of-the-art.