Is dynamics prediction indispensable for physical reasoning? If so, what kind of roles do the dynamics prediction modules play during the physical reasoning process? Most studies focus on designing dynamics prediction networks and treating physical reasoning as a downstream task without investigating the questions above, taking for granted that the designed dynamics prediction would undoubtedly help the reasoning process. In this work, we take a closer look at this assumption, exploring this fundamental hypothesis by comparing two learning mechanisms: Learning from Dynamics (LfD) and Learning from Intuition (LfI). In the first experiment, we directly examine and compare these two mechanisms. Results show a surprising finding: Simple LfI is better than or on par with state-of-the-art LfD.

Spiking Neural Networks (SNNs) are promising brain-inspired models known for low power consumption and superior potential for temporal processing, but identifying suitable learning mechanisms remains a challenge. Despite the presence of multiple coexisting learning strategies in the brain, current SNN training methods typically rely on a single form of synaptic plasticity, which limits their adaptability and representational capability. In this paper, we propose a biologically inspired training framework that incorporates multiple synergistic plasticity mechanisms for more effective SNN training. Our method enables diverse learning algorithms to cooperatively modulate the accumulation of information, while allowing each mechanism to preserve its own relatively independent update dynamics. We evaluated our approach on both static image and dynamic neuromorphic datasets to demonstrate that our framework significantly improves performance and robustness compared to conventional learning mechanism models. This work provides a general and extensible foundation for developing more powerful SNNs guided by multi-strategy brain-inspired learning.

Reinforcement Learning (RL) agents often exhibit learning behaviors that are not intuitively interpretable by human observers, which can result in suboptimal feedback in collaborative teaching settings. Yet, how humans perceive and interpret RL agent's learning behavior is largely unknown. In a bottom-up approach with two experiments, this work provides a data-driven understanding of the factors of human observers' understanding of the agent's learning process. A novel, observation-based paradigm to directly assess human inferences about agent learning was developed. In an exploratory interview study (\textit{N}=9), we identify four core themes in human interpretations: Agent Goals, Knowledge, Decision Making, and Learning Mechanisms. A second confirmatory study (\textit{N}=34) applied an expanded version of the paradigm across two tasks (navigation/manipulation) and two RL algorithms (tabular/function approximation). Analyses of 816 responses confirmed the reliability of the paradigm and refined the thematic framework, revealing how these themes evolve over time and interrelate. Our findings provide a human-centered understanding of how people make sense of agent learning, offering actionable insights for designing interpretable RL systems and improving transparency in Human-Robot Interaction.

Human learning relies on specialization--distinct cognitive mechanisms working together to enable rapid learning. In contrast, most modern neural networks rely on a single mechanism: gradient descent over an objective function. This raises the question: might human learners' relatively rapid learning from just tens of examples instead of tens of thousands in data-driven deep learning arise from our ability to use multiple specialized mechanisms of learning in combination? We investigate this question through an ablation analysis of inductive human learning simulations in online tutoring environments. Comparing reinforcement learning to a more data-efficient 3-mechanism symbolic rule induction approach, we find that decomposing learning into multiple distinct mechanisms significantly improves data efficiency, bringing it in line with human learning. Furthermore, we show that this decomposition has a greater impact on efficiency than the distinction between symbolic and subsymbolic learning alone. Efforts to align data-driven machine learning with human learning often overlook the stark difference in learning efficiency. Our findings suggest that integrating multiple specialized learning mechanisms may be key to bridging this gap. A key idea within the learning sciences, popularized by Anderson's ACT -R theory (2013) and expanded upon by others (Koedinger, Corbett, & Perfetti, 2012), is that human performance is enabled by independent knowledge components--individual facts, skills, or principles--that must be understood and retained to exhibit mastery of higher-level capabilities.

Collective Learning Mechanism based Optimal Transport Generative Adversarial Network for Non-parallel V oice Conversion Sandipan Dhar 1, Md. Email: sandipandhartsk03@gmail.com, tousin@cse.iitb.ac.in, ndjana.cse@nitdgp.ac.in, swagatam.das@isical.ac.in Abstract --After demonstrating significant success in image synthesis, Generative Adversarial Network (GAN) models have likewise made significant progress in the field of speech synthesis, leveraging their capacity to adapt the precise distribution of target data through adversarial learning processes. Notably, in the realm of State-Of-The-Art (SOT A) GAN-based V oice Conversion (VC) models, there exists a substantial disparity in naturalness between real and GAN-generated speech samples. Furthermore, while many GAN models currently operate on a single generator discriminator learning approach, optimizing target data distribution is more effectively achievable through a single generator multi-discriminator learning scheme. Hence, this study introduces a novel GAN model named Collective Learning Mechanism-based Optimal Transport GAN (CLOT - GAN) model, incorporating multiple discriminators, including the Deep Convolutional Neural Network (DCNN) model, Vision Transformer (ViT), and conformer . The objective of integrating various discriminators lies in their ability to comprehend the formant distribution of mel-spectrograms, facilitated by a collective learning mechanism. Simultaneously, the inclusion of Optimal Transport (OT) loss aims to precisely bridge the gap between the source and target data distribution, employing the principles of OT theory.

Is dynamics prediction indispensable for physical reasoning? If so, what kind of roles do the dynamics prediction modules play during the physical reasoning process? Most studies focus on designing dynamics prediction networks and treating physical reasoning as a downstream task without investigating the questions above, taking for granted that the designed dynamics prediction would undoubtedly help the reasoning process. In this work, we take a closer look at this assumption, exploring this fundamental hypothesis by comparing two learning mechanisms: Learning from Dynamics (LfD) and Learning from Intuition (LfI). In the first experiment, we directly examine and compare these two mechanisms. Results show a surprising finding: Simple LfI is better than or on par with state-of-the-art LfD.

Although Reinforcement Learning (RL) algorithms acquire sequential behavioral patterns through interactions with the environment, their effectiveness in noisy and high-dimensional scenarios typically relies on specific structural priors. In this paper, we propose a novel and general Structural Information principles-based framework for effective Decision-Making, namely SIDM, approached from an information-theoretic perspective. This paper presents a specific unsupervised partitioning method that forms vertex communities in the state and action spaces based on their feature similarities. An aggregation function, which utilizes structural entropy as the vertex weight, is devised within each community to obtain its embedding, thereby facilitating hierarchical state and action abstractions. By extracting abstract elements from historical trajectories, a directed, weighted, homogeneous transition graph is constructed. The minimization of this graph's high-dimensional entropy leads to the generation of an optimal encoding tree. An innovative two-layer skill-based learning mechanism is introduced to compute the common path entropy of each state transition as its identified probability, thereby obviating the requirement for expert knowledge. Moreover, SIDM can be flexibly incorporated into various single-agent and multi-agent RL algorithms, enhancing their performance. Finally, extensive evaluations on challenging benchmarks demonstrate that, compared with SOTA baselines, our framework significantly and consistently improves the policy's quality, stability, and efficiency up to 32.70%, 88.26%, and 64.86%, respectively.

The adoption of Reinforcement Learning (RL) in several human-centred applications provides robots with autonomous decision-making capabilities and adaptability based on the observations of the operating environment. In such scenarios, however, the learning process can make robots' behaviours unclear and unpredictable to humans, thus preventing a smooth and effective Human-Robot Interaction (HRI). As a consequence, it becomes crucial to avoid robots performing actions that are unclear to the user. In this work, we investigate whether including human preferences in RL (concerning the actions the robot performs during learning) improves the transparency of a robot's behaviours. For this purpose, a shielding mechanism is included in the RL algorithm to include human preferences and to monitor the learning agent's decisions. We carried out a within-subjects study involving 26 participants to evaluate the robot's transparency in terms of Legibility, Predictability, and Expectability in different settings. Results indicate that considering human preferences during learning improves Legibility with respect to providing only Explanations, and combining human preferences with explanations elucidating the rationale behind the robot's decisions further amplifies transparency. Results also confirm that an increase in transparency leads to an increase in the safety, comfort, and reliability of the robot. These findings show the importance of transparency during learning and suggest a paradigm for robotic applications with human in the loop.

What are the computational foundations of social grouping? Traditional approaches to this question have focused on verbal reasoning or simple (low-dimensional) quantitative models. In the real world, however, social preferences emerge when high-dimensional learning systems (brains and bodies) interact with high-dimensional sensory inputs during an animal's embodied interactions with the world. A deep understanding of social grouping will therefore require embodied models that learn directly from sensory inputs using high-dimensional learning mechanisms. To this end, we built artificial neural networks (ANNs), embodied those ANNs in virtual fish bodies, and raised the artificial fish in virtual fish tanks that mimicked the rearing conditions of real fish. We then compared the social preferences that emerged in real fish versus artificial fish. We found that when artificial fish had two core learning mechanisms (reinforcement learning and curiosity-driven learning), artificial fish developed fish-like social preferences. Like real fish, the artificial fish spontaneously learned to prefer members of their own group over members of other groups. The artificial fish also spontaneously learned to self-segregate with their in-group, akin to self-segregation behavior seen in nature. Our results suggest that social grouping can emerge from three ingredients: (1) reinforcement learning, (2) intrinsic motivation, and (3) early social experiences with in-group members. This approach lays a foundation for reverse engineering animal-like social behavior with image-computable models, bridging the divide between high-dimensional sensory inputs and social preferences.

Financial sector and especially the insurance industry collect vast volumes of text on a daily basis and through multiple channels (their agents, customer care centers, emails, social networks, and web in general). The information collected includes policies, expert and health reports, claims and complaints, results of surveys, and relevant social media posts. It is difficult to effectively extract label, classify, and interpret the essential information from such varied and unstructured material. Therefore, the Insurance Industry is among the ones that can benefit from applying technologies for the intelligent analysis of free text through Natural Language Processing (NLP). In this paper, CRL+, a novel text classification model combining Contrastive Representation Learning (CRL) and Active Learning is proposed to handle the challenge of using semi-supervised learning for text classification. In this method, supervised (CRL) is used to train a RoBERTa transformer model to encode the textual data into a contrastive representation space and then classify using a classification layer. This (CRL)-based transformer model is used as the base model in the proposed Active Learning mechanism to classify all the data in an iterative manner. The proposed model is evaluated using unstructured obituary data with objective to determine the cause of the death from the data. This model is compared with the CRL model and an Active Learning model with the RoBERTa base model. The experiment shows that the proposed method can outperform both methods for this specific task.