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.
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.
New algorithm trains neural nets on simple skills to learn complex tasks faster.
problem Learning complex tasks through simple imitation.
method Train neural networks on simple, easy-to-learn skills to accelerate learning of complex, hard-to-learn tasks.
result Consistently outperforms state-of-the-art baseline in training speed and performance.
Transformers prefer simpler explanations in hierarchical tasks.
problem Navigating tasks with varying complexity levels.
method Well-controlled testbeds based on Markov chains and linear regression.
result Transformers favor the least complex sufficient explanation when presented with simpler data.
New algorithm reduces sample complexity for multi-task bandits.
problem Optimizing representation and predictor pairs for multi-task bandits.
method OSRL-SC algorithm with sample complexity H(Glog(1/δG)+Xlog(1/δH)). result OSRL-SC algorithm approaches sample complexity lower bounds.
Single neural network learns multiple tasks from combined data.
problem Can a single neural network learn multiple unrelated tasks?
method Investigates how task representations affect joint learning; uses various task encoding methods.
result Single neural network can learn multiple tasks from combined data, even when tasks are unrelated and different.
Near-optimal rates for multi-task learning with shared representations.
problem Approximation and statistical complexity of learning multiple operators.
method Multiple Neural Operators (MNO) architecture and comparison with DeepONet.
result Near-optimal upper and lower bounds for approximation and generalization.
We study a recent model of collaborative PAC learning where k players with k different tasks collaborate to learn a single classifier that works for all tasks. Previous work showed that when there is a classifier that has very small error on all tasks, there is a collaborative algorithm that finds a single classifi…
Transferring knowledge across a sequence of reinforcement-learning tasks is challenging, and has a number of important applications. Though there is encouraging empirical evidence that transfer can improve performance in subsequent reinforcement-learning tasks, there has been very little theoretical analysis. In this p…
A language for specifying complex reinforcement learning tasks.
problem Challenges in specifying and shaping reward functions for complex reinforcement learning tasks.
method Proposes a new language and algorithm for automatically generating and shaping reward functions.
result SPECTRL tool outperforms state-of-the-art baselines.
New statistical guarantees for transfer learning with diverse tasks.
problem Statistical guarantees for transfer learning across different tasks.
method Formal analysis of t+1 tasks with shared representation. result Sample complexity reduction for new tasks using shared representation.
One-layer transformers can't solve induction heads task efficiently.
problem Solving the induction heads task efficiently with one-layer transformers.
method Communication complexity argument showing exponential size requirement.
result No one-layer transformer can solve the induction heads task efficiently.
Complex-valued neural networks are not a new concept, however, the use of real-valued models has often been favoured over complex-valued models due to difficulties in training and performance. When comparing real-valued versus complex-valued neural networks, existing literature often ignores the number of parameters, r…
Proposes Neural Complexity (NC) for predicting and explaining generalization in deep neural networks.
problem Challenges in specifying a suitable complexity measure for deep neural networks to predict and explain generalization.
method A meta-learning framework that learns a scalar complexity measure through interactions with many heterogeneous tasks.
result Trained NC model can be added to standard training loss to regularize any task learner.
CVRL tackles complex visual observations in reinforcement learning.
problem Complex visual observations in natural environments.
method Contrastive Variational Reinforcement Learning (CVRL) learns a contrastive variational model by maximizing mutual information between latent states and observations.
result CVRL achieves comparable performance with state-of-the-art model-based DRL methods and significantly outperforms them on tasks with complex observations.
MoEs can efficiently model complex tasks with low-dimensionality and sparsity.
problem Understanding the theoretical foundations of MoEs for complex tasks.
method Systematic study of MoEs with two structural priors: low-dimensionality and sparsity.
result MoEs can approximate functions on low-dimensional manifolds and exhibit exponential structured tasks.
Transformers capture combinatorial tasks with bounded error and logarithmic sample dependence.
problem Capturing complex combinatorial tasks with bounded error and sample efficiency.
method Formal definition of algorithmic capture, empirical analysis of infinite-width transformers, upper bounds on computational complexity.
result Transformers exhibit an inductive bias favoring simpler algorithmic procedures over higher complexity ones.
This work improves RL for complex robotic tasks by guiding exploration with task-specific goal distributions.
problem Solving long-horizon, complex sequential tasks in robotics with sparse rewards.
method Extends hindsight relabelling to task-specific goal distributions using a small set of demonstrations.
result Significantly higher overall performance on complex robotic manipulation tasks.
CMDE uses deep learning to estimate causal effects from complex data.
problem Handling complex data structures like images for causal effect estimation.
method Causal Multi-task Deep Ensemble (CMDE) framework.
result CMDE outperforms state-of-the-art methods across various datasets and 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.
Align-RUDDER improves reinforcement learning with few demonstrations by redistributing rewards.
problem Learning complex tasks with sparse and delayed rewards using few demonstrations.
method Align-RUDDER uses a profile model for reward redistribution based on multiple sequence alignment of demonstrations.
result Align-RUDDER outperforms competitors on complex tasks with few demonstrations.
Paper proposes an algorithm for lifelong learning with shared structure.
problem Lifelong learning with shared structure in an online setting.
method Proposes a simple algorithm using multi-task empirical risk minimization.
result Establishes a sample complexity bound based on task-eluder dimension.
Complex numbers have long been favoured for digital signal processing, yet complex representations rarely appear in deep learning architectures. RNNs, widely used to process time series and sequence information, could greatly benefit from complex representations. We present a novel complex gated recurrent cell, which i…
Shaping in humans and animals has been shown to be a powerful tool for learning complex tasks as compared to learning in a randomized fashion. This makes the problem less complex and enables one to solve the easier sub task at hand first. Generating a curriculum for such guided learning involves subjecting the agent to…
Efficient streaming algorithms for robust statistics with near-optimal memory.
problem High-dimensional robust statistics tasks in streaming model.
method First efficient streaming algorithms with near-optimal memory requirements.
result Near-optimal error guarantees and space complexity nearly-linear in the dimension for robust mean estimation.
This work improves sample efficiency in meta-learning for nonlinear tasks.
problem Learning complex tasks efficiently with limited data.
method Subspace-based representations for nonlinear tasks.
result Subspace-based representations can be learned efficiently and improve future task performance.
Predicting the runtime complexity of a programming code is an arduous task. In fact, even for humans, it requires a subtle analysis and comprehensive knowledge of algorithms to predict time complexity with high fidelity, given any code. As per Turing's Halting problem proof, estimating code complexity is mathematically…
Study task-guided exploration in linear dynamical systems, improving sample complexity.
problem Efficiently learning about an environment to complete a specific task.
method Proposed a computationally efficient experiment-design based exploration algorithm.
result Optimally explores the environment, collecting precise information needed to complete the task.
The paper presents a new framework for complex Support Vector Regression as well as Support Vector Machines for quaternary classification. The method exploits the notion of widely linear estimation to model the input-out relation for complex-valued data and considers two cases: a) the complex data are split into their …
WILD-SCAV benchmarks AI in complex 3D FPS environments.
problem Lack of complexity and diversity in RL environments.
method Developed a 3D open-world FPS game environment.
result Demonstrates effectiveness in benchmarking RL algorithms.
Transformer architecture struggles with complex tasks due to limitations in function composition.
problem Transformer architecture's limitations in handling complex tasks.
method Used Communication Complexity to prove limitations in composing functions.
result Transformer layer is incapable of handling large domain functions, even when domains are small.
New method improves hyperparameter tuning efficiency across similar tasks.
problem Mismatch between evaluations in current and previous tasks.
method Nested drop-out and auto-relevance determination for learning basis functions of increasing complexity.
result Improves sample efficiency in hyperparameter tuning across different data regimes.
Many continuous control tasks have easily formulated objectives, yet using them directly as a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many classical control tasks guide RL training using complex rewards, which require tedious hand-tuning. We automate the reward search with AutoRL,…
We introduce an asymmetric distance in the space of learning tasks, and a framework to compute their complexity. These concepts are foundational for the practice of transfer learning, whereby a parametric model is pre-trained for a task, and then fine-tuned for another. The framework we develop is non-asymptotic, captu…
This paper addresses the meta-learning problem in sparse linear regression with infinite tasks. We assume that the learner can access several similar tasks. The goal of the learner is to transfer knowledge from the prior tasks to a similar but novel task. For p parameters, size of the support set k , and l samples per …
Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during…
New findings on complexity limits in fixed budget bandit identification.
problem Determining the best possible error rate for fixed budget bandit identification.
method Analyzing the best non-adaptive sampling procedures and showing the existence of complexities.
result No fixed complexity for certain bandit identification tasks.
Proposes efficient model for continual learning that grows model over task-specific parameters.
problem Limited transfer learning ability and forgetting of earlier knowledge in existing methods.
method Filter and channel expansion method that grows model over previous task parameters.
result Better knowledge transfer and improved performance in task incremental learning.
Weakly-supervised RL identifies meaningful tasks, improving performance in complex environments.
problem Learning to efficiently explore and distinguish between meaningful and irrelevant tasks.
method Weak supervision to automatically disentangle meaningful tasks from a large space of nonsensical tasks.
result The learned subspace of meaningful tasks leads to substantial performance gains, especially in complex environments.
This paper investigates multi-task reinforcement learning in non-Markovian decision making, showing benefits in sample efficiency.
problem Investigating multi-task reinforcement learning in non-Markovian decision making processes.
method Developed a joint model class for tasks and used the η-bracketing number to quantify complexity and similarity. result Multi-task reinforcement learning can improve sample efficiency in non-Markovian decision making processes.
Neuro-inspired recurrent neural network algorithms, such as echo state networks, are computationally lightweight and thereby map well onto untethered devices. The baseline echo state network algorithms are shown to be efficient in solving small-scale spatio-temporal problems. However, they underperform for complex task…
SAIL learns from sub-optimal demonstrations to improve sample efficiency in sparse reward tasks.
problem Reducing sample complexity in sparse-rewarded tasks.
method Self-Adaptive Imitation Learning (SAIL) that exploits sub-optimal demonstrations and efficient exploration.
result Significantly improved sample efficiency and better final performance across various tasks.
The paper explores how LLMs with CoT improve performance on complex tasks.
problem Understanding the mechanisms behind LLMs' improved performance with CoT.
method Using circuit complexity theory, the paper examines LLMs' expressivity in solving mathematical and decision-making problems.
result LLMs with CoT can generate correct solutions step-by-step, even for complex tasks.
Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network parameters, which performs multiple tasks concurrently. However such compound polic…
Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on these latent representations, but the field still lacks a large-scale standard …
We propose reinforcement learning on simple networks consisting of random connections of spiking neurons (both recurrent and feed-forward) that can learn complex tasks with very little trainable parameters. Such sparse and randomly interconnected recurrent spiking networks exhibit highly non-linear dynamics that transf…
Study shows memory needs grow with task sequence length in continual learning.
problem Challenges in retaining aptitude for multiple learning tasks sequentially.
method Complexity-theoretic study using communication complexity and multiplicative weights update.
result Memory needs grow linearly with task sequence length, suggesting intractability.
Meta-learning improves support recovery in high-dimensional PCA.
problem Support recovery in high-dimensional Principal Component Analysis.
method Meta-learning approach to reduce sample complexity and support recovery.
result Support recovery can be achieved with significantly fewer samples than traditional methods.