Method infers internal model from rational foraging behavior.
problem Discover how the brain represents and computes dynamic beliefs.
method POMDP model, EM algorithm, maximum likelihood estimation.
result Successfully recovered internal model and reward function of foraging agents.
MAYA learns bee foraging decisions with limited memory.
problem Reproducing and predicting bees' foraging decisions with limited memory.
method Sequential imitation learning model based on multi-armed bandits, considering a temporal window τ of 7 trials.
result MAYA outperforms imitation baselines and classical models, providing interpretability and realistic trajectories.
New method extends supervised learning for non-stationary control problems.
problem Optimal control in non-stationary, reset-free environments.
method Prospective Learning with Control (PLuC) using Empirical Risk Minimization (ERM).
result ERM asymptotically achieves Bayes optimal policy in non-stationary environments.
Simpler ε-greedy with longer action durations improves exploration.
problem Limited exploration capability of ε-greedy in complex domains.
method Temporally extended ε-greedy with repeated actions for random durations.
result Temporally extended ε-greedy outperforms sophisticated methods on various domains.
Prospective learning improves AI performance in changing conditions.
problem Machine learning algorithms struggle with changing data distributions and evolving goals.
method Developed a new mathematical framework called Prospective Learning.
result Preliminary results show improved algorithm performance and applicability to sequential decision-making.
Model shows significant income inequality emerges from equal opportunities in a simple economy.
problem Income inequality in a simple foraging economy.
method Minimal, endogenous model of a simple foraging economy.
result Stochastic income distributions from the model match empirical data.
New framework tackles deep financial reporting bottleneck by improving hallucination and coherence.
problem Statistical smoothing trap in LLMs limits deep financial reporting quality.
method DeepNews Framework integrates information foraging, schema-guided planning, and adversarial prompting.
result DeepNews system achieves 25% acceptance rate in blind test, significantly outperforming SOTA.
Paper proposes DAC-ML, a cognitive architecture that learns quickly from few episodes.
problem Sample inefficiency in AI learning action policies.
method Incorporates hippocampus-inspired sequential memory system into DAC theory of mind.
result DAC-ML rapidly converges to effective action policies maximizing reward.
Enactive learning shows agents can learn from their environment, but limited by action choices.
problem Learning and interaction of autonomous agents in complex environments.
method Simulation of artificial agents in maze environments, comparing enactive learning to classical reinforcement learning.
result Enactive agents can learn to avoid unfavorable interactions but performance is limited by action choices.
Modeling high-frequency speculative markets as auction search processes.
problem Understanding trading dynamics in high-frequency order-driven markets.
method Total order book model with diffusion-drift-reaction model, inspired by foraging and chemotaxis.
result Analytic and numerical analysis of trading performance in various search mechanisms.
Analyzes Lévy flights on manifolds for finding small targets.
problem Finding small targets using Lévy flights on various manifolds.
method Analytic description of Lévy flights on closed Riemannian manifolds, including asymptotics of expected stopping time.
result Computes the expected time for finding a small target by Lévy flight on surfaces.
Ant colonies and boosting algorithms both reduce bias and variance through adaptive mechanisms.
problem Understanding the mathematical principles behind ensemble learning and ant colony behavior.
method Developed a formal mapping between AdaBoost's adaptive reweighting and ant recruitment dynamics.
result Proved that the fundamental theorem of weak learnability has a direct analog in colony decision-making.
Ensembles of neural networks learn better by sharing information.
problem Improving performance of neural networks through collective learning.
method Modeling neural networks as socially interacting agents aiming to maximize their own performance and functional relations to others.
result Optimal collective performance emerges from local interactions between networks, leading to specialization and higher confidence.
This paper uses ML to identify prey handling in seals.
problem Automatically classify prey handling activity in seals for monitoring.
method Developed and compared three ML algorithms: Input Delay Neural Networks, Support Vector Machines, and Echo State Networks.
result Echo State Networks outperformed other algorithms in terms of accuracy and F1score.
This paper reviews dMTL and methods for selecting auxiliary tasks.
problem Improving model performance for multiple tasks.
method Review of dMTL approaches and methods for selecting auxiliary tasks.
result Methods for selecting auxiliary tasks can improve dMTL performance.
APT-Gen generates tasks to help RL learn in hard problems.
problem Learning in hard exploration problems.
method APT-Gen uses a task generator to create tasks from a parameterized space, balancing performance and similarity to target tasks.
result APT-Gen outperforms baselines in grid world and robotic manipulation tasks.
OCEAN infers online task identities from context variables.
problem Online task inference for compositional tasks with context adaptation.
method Variational inference framework OCEAN models global and local context variables in a joint latent space.
result OCEAN provides more effective task inference with sequential context adaptation.
Deep RL multi-task learning outperforms single-task learning on new tasks.
problem Improving performance on new tasks in multi-task reinforcement learning.
method Investigation of multi-task reinforcement learning algorithms with and without Elastic Weight Consolidation (EWC).
result Multi-task reinforcement learning algorithms outperform single-task learning on new tasks.
Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between …
Proposes a new method for clustering tasks in multi-task learning.
problem Improving performance of multiple related prediction tasks.
method Semisoft task clustering approach with a three-step algorithm.
result Validation of the proposed approach on synthetic and real-world datasets.
MBML improves multi-task RL by inferring task identity from state-action pairs.
problem Multi-task batch reinforcement learning with unseen tasks.
method MBML uses triplet loss and relabeling to robustify task inference.
result Significantly faster convergence on unseen tasks compared to random initialization.
Multi-task learning is a learning paradigm which seeks to improve the generalization performance of a learning task with the help of some other related tasks. In this paper, we propose a regularization formulation for learning the relationships between tasks in multi-task learning. This formulation can be viewed as a n…
HydaLearn dynamically adjusts task weights for better MTL performance.
problem Constant loss weights in MTL lead to poor results due to drifting relevance and varying mini-batch composition.
method HydaLearn uses mini-batch gradients to dynamically adjust task weights.
result HydaLearn improves performance on synthetic and real-world data.
AutoSeM automatically selects and balances auxiliary tasks in MTL.
problem Choosing and balancing auxiliary tasks in MTL.
method AutoSeM uses a Beta-Bernoulli multi-armed bandit with Thompson Sampling for task selection and a Gaussian Process for learning the mixing ratio.
result AutoSeM achieves significant performance boosts on GLUE language understanding tasks.
New distance metric for neural architecture search reduces search space complexity.
problem Reducing the complexity of neural architecture search.
method Fisher task distance for measuring task similarity and online neural architecture search.
result Reduced search space complexity for task-specific architectures.
HGNN learns augmented features for deep multi-task learning.
problem Feature learning for deep multi-task learning.
method Hierarchical Graph Neural Network (HGNN) with two levels of graph neural networks.
result Significant performance improvement in classification tasks.
We investigate task clustering for deep-learning based multi-task and few-shot learning in a many-task setting. We propose a new method to measure task similarities with cross-task transfer performance matrix for the deep learning scenario. Although this matrix provides us critical information regarding similarity betw…
ST-MAML tackles task ambiguity in meta-learning by encoding tasks with stochastic representations.
problem Handling tasks from multiple distributions is challenging for meta-learning due to task ambiguity.
method ST-MAML uses a stochastic neural network module to encode tasks and propagate task representations to revise input variable encoding.
result ST-MAML matches or outperforms state-of-the-art methods on various tasks.
New algorithm combines curriculum learning with HER for complex object manipulation tasks.
problem Learning complex sequential object manipulation tasks from scratch is challenging.
method Curriculum learning with Hindsight Experience Replay (HER) for recurrent object manipulation tasks.
result Significant improvement in learning sequential object manipulation tasks compared to vanilla-HER.
Transformers infer tasks from context via two modes, geometrically shaped task vectors explain their behavior.
problem Understanding how transformers infer tasks from context and the geometric properties of task vectors.
method Synthetic setting to train small transformers, mathematical characterization of task-vector geometry and inference modes.
result Task-vector geometry shapes in-distribution and out-of-distribution behavior of transformers.
MTL-NAS combines NAS with GP-MTL for task-agnostic multi-task learning.
problem Designing architectures for diverse tasks with varying priors.
method Disentangled GP-MTL networks, hierarchical feature sharing, and gradient-based search.
result General-purpose model trained once can adapt to multiple tasks.
Meta-learning framework uses task similarity through nonparametric kernel regression.
problem Limited tasks and outliers/dissimilar tasks hinder meta-learning performance.
method Nonparametric kernel regression to quantify and use task similarity.
result Meta-learning algorithm outperforms existing methods in task-limited settings.
Novel meta-RL strategy improves efficiency in learning novel tasks.
problem Efficiency in learning novel tasks using deep RL.
method Decomposes meta-RL into task-exploration, task-inference, and task-fulfillment; uses deep networks and a task encoder.
result Improves sample efficiency and mitigates meta-overfitting.
RTE enables extrapolation to new tasks by learning task transformations.
problem Learning systems struggle to generalize to unseen tasks.
method Relational Task Extrapolator (RTE) learns task transformations to enable extrapolation.
result RTE substantially outperforms existing approaches on extrapolation tasks.
Study shows perceptual boost of visual attention varies with task difficulty and size.
problem Understanding how task-dependent the perceptual boost of visual attention is in natural settings.
method Designed and trained neural networks on various visual tasks, comparing results to baseline.
result Perceptual boost of attention is stronger with more difficult tasks and weaker with larger task sets.
New approach for multi-task reinforcement learning without task interference.
problem Efficient knowledge sharing between tasks in reinforcement learning.
method Attention-based multi-task deep reinforcement learning.
result Achieves positive knowledge transfer and avoids negative transfer.
Meta-RL learns shared and task-specific information for quick adaptation.
problem Data inefficiency and limited generalization in deep RL.
method Task embedding and shared policy learned via SGD meta-learner.
result 3 to 4 times higher returns on novel tasks compared to baselines.
Multi-task learning (MTL) has recently contributed to learning better representations in service of various NLP tasks. MTL aims at improving the performance of a primary task, by jointly training on a secondary task. This paper introduces automated tasks, which exploit the sequential nature of the input data, as second…
Robot learns multiple tasks hierarchically by transferring knowledge.
problem Learning multiple complex tasks in open-ended environments.
method Task-oriented procedures, goal-babbling, imitation learning, active learning, intrinsic motivation.
result Robots can learn complex tasks more efficiently by transferring knowledge from simpler ones.
In the paradigm of multi-task learning, mul- tiple related prediction tasks are learned jointly, sharing information across the tasks. We propose a framework for multi-task learn- ing that enables one to selectively share the information across the tasks. We assume that each task parameter vector is a linear combi- nat…
Transformers can generalize to a large task family with only a few demonstrations.
problem Can learning from a small set of tasks generalize to a large task family?
method Investigating autoregressive compositional structure where each task is a composition of T T T operations, each from a finite family of D D D subtasks. result Transformers can generalize to D T D^T D T tasks with only O ~ ( D ) \widetilde{O}(D) O ( D ) demonstrations. Framework adapts to new tasks based on prior knowledge.
problem Models struggle to adapt to novel tasks without direct experience.
method Learned task representations and meta-mappings to transform them.
result Meta-mapping achieves 80-90% performance on novel tasks.
Gradient surgery improves multi-task learning efficiency.
problem Challenges in sharing structure across multiple tasks.
method Gradient projection onto normal plane of conflicting gradients.
result Substantial gains in efficiency and performance.
TOG-Net optimizes grasping for tool manipulation in simulated self-supervised learning.
problem Optimizing grasping for tool manipulation in robots.
method Simulated self-supervised learning with Task-Oriented Grasping Network (TOG-Net).
result Achieved 71.1% task success rate for sweeping and 80.0% for hammering.
Method reweights auxiliary tasks to reduce data need for main task.
problem Limited labeled data for supervised learning.
method Formulates weighted likelihood function as surrogate prior, minimizing divergence to true prior.
result Effective use of limited labeled data with auxiliary tasks, improving performance.
SON-GOKU uses graph coloring to improve multi-task learning by partitioning tasks into compatible groups.
problem Gradient interference between conflicting multi-task learning objectives slows convergence and model performance.
method SON-GOKU computes gradient interference, constructs an interference graph, and applies greedy graph-coloring to partition tasks.
result SON-GOKU consistently outperforms baselines and state-of-the-art multi-task optimizers on six datasets.
Paper tackles graph class-incremental learning with task profiling and prompting.
problem Challenges in separating classes from different tasks in graph CIL.
method Laplacian smoothing-based task profiling and graph prompting approach.
result 100% task ID prediction accuracy and significant performance improvement.
Optimal task order improves continual learning performance.
problem Challenges in neural networks learning multiple tasks in sequence.
method Linear teacher-student model with latent factors, derived analytical expression.
result Two principles for optimal task order: least representative first and dissimilar adjacent tasks.