Paper introduces a new curriculum generation method for reinforcement learning.
problem Improving reinforcement learning performance and speed through curriculum learning.
method The paper proposes a novel curriculum generation paradigm based on progression and mapping functions.
result Empirical results show the new approach outperforms state-of-the-art algorithms.
Analyzes when and why curricula help neural networks learn.
problem Why and when does curriculum learning help neural networks?
method Statistical physics methods applied to a neural network model.
result Curricula can modestly speed up learning but do not provide generalization benefit.
Curriculum learning shows marginal benefits over random ordering on standard datasets.
problem Investigating the benefits of curriculum learning over random ordering in training neural networks.
method Experiments with curriculum, anti-curriculum, and random-curriculum orderings on various datasets and conditions.
result Curriculum learning only marginally improves performance on standard datasets and is outperformed by random ordering.
Automatically generates a deep RL curriculum for faster and more stable learning.
problem How to automatically generate a curriculum for deep RL agents.
method Interprets curriculum generation as an inference problem, learning task distributions progressively.
result Curricula significantly improve learning performance across various environments and deep RL algorithms.
Unified framework for multi-objective curriculum learning in robotics.
problem Improving sample efficiency and final performance in robotic policy learning.
method Unified automatic curriculum learning framework with multi-task hyper-net and flexible memory mechanism.
result Superior performance compared to state-of-the-art methods in robotic manipulation tasks.
Curriculum learning speeds up agent learning in Minecraft, a complex visual domain.
problem Training agents to learn multiple tasks in a complex, visual domain.
method Learning-progress based curriculum and dynamic exploration bonuses.
result Curriculum learning improves agent performance in a complex reinforcement learning problem.
Curriculum learning in reinforcement learning is a training methodology that seeks to speed up learning of a difficult target task, by first training on a series of simpler tasks and transferring the knowledge acquired to the target task. Automatically choosing a sequence of such tasks (i.e. a curriculum) is an open pr…
Curriculum learning and imitation learning improve control over financial time-series data.
problem Improving control performance over complex financial time-series data.
method Data augmentation for curriculum learning and policy distillation for imitation learning.
result Curriculum learning shows significant improvement over time-series control 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.
Curriculum learning in reinforcement learning is used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely applied in both animal training and pedagogy. In reinforcement learning, all previous task sequencing methods have shaped exploration with …
The paper studies the benefits of curriculum learning in linear regression tasks.
problem Theoretical understanding of curriculum learning's benefits in machine learning.
method Theoretical analysis of curriculum learning in structured and unstructured multitask linear regression problems.
result Adaptive learning in the unstructured setting is fundamentally harder than oracle learning, but not in the structured setting.
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…
Survey on curriculum learning for reinforcement learning.
problem Efficiently learning complex tasks in reinforcement learning.
method Framework for curriculum learning in reinforcement learning.
result Survey and classification of existing CL methods.
In this paper, we investigate a new form of automated curriculum learning based on adaptive selection of accuracy requirements, called accuracy-based curriculum learning. Using a reinforcement learning agent based on the Deep Deterministic Policy Gradient algorithm and addressing the Reacher environment, we first show …
Q-CurL optimizes quantum learning with a curriculum design.
problem Efficiently training quantum models with limited resources.
method Quantum curriculum learning framework.
result Q-CurL enhances training convergence and generalization.
EPC curriculum improves MARL performance as agent population grows.
problem Challenges in learning good policies for large multi-agent systems.
method Evolutionary Population Curriculum (EPC) for scaling MARL.
result EPC consistently outperforms baselines as agent population increases.
Humans tend to learn complex abstract concepts faster if examples are presented in a structured manner. For instance, when learning how to play a board game, usually one of the first concepts learned is how the game ends, i.e. the actions that lead to a terminal state (win, lose or draw). The advantage of learning end-…
Curriculum learning helps neural networks learn parities more efficiently.
problem Improving learning efficiency for neural networks on parity targets.
method Using a curriculum learning approach with a mixture of sparse and dense inputs.
result A 2-layer ReLU neural network can learn parities more efficiently than a fully connected network.
CP-DRL improves curriculum reinforcement learning by leveraging causal relationships.
problem Designing effective task sequences for reinforcement learning.
method Causal-Paced Deep Reinforcement Learning (CP-DRL) that approximates SCM differences based on interaction data.
result CP-DRL outperforms existing methods on benchmarks, achieving faster convergence and higher returns.
ACL improves DRL by adapting task difficulty to agent's capabilities.
problem Improving sample efficiency and performance in DRL.
method Adapting task difficulty based on agent's capacity.
result Enhanced sample efficiency and asymptotic performance.
In this paper we introduce Curriculum GANs, a curriculum learning strategy for training Generative Adversarial Networks that increases the strength of the discriminator over the course of training, thereby making the learning task progressively more difficult for the generator. We demonstrate that this strategy is key …
Bi-directional Curriculum Learning improves graph anomaly detection by considering both homogeneity and heterogeneity.
problem Existing graph anomaly detection methods often ignore the different contributions of nodes to training.
method Introduces Bi-directional Curriculum Learning (BCL) to optimize GAD methods by considering both homogeneity and heterogeneity of nodes.
result Extensive experiments show that BCL significantly improves the performance of GAD anomaly detection models.
Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the completion of some goal. Goal-directed RL has seen large gains in sample efficiency, due to the ease of reusing or generating new experience by pro…
Training generative models like Generative Adversarial Network (GAN) is challenging for noisy data. A novel curriculum learning algorithm pertaining to clustering is proposed to address this issue in this paper. The curriculum construction is based on the centrality of underlying clusters in data points. The data point…
SAMPLR optimizes for ground truth in aleatoric parameters to avoid curriculum-induced covariate shift.
problem Curriculum learning shifts training distribution, leading to suboptimal policies in aleatoric settings.
method SAMPLR optimizes ground-truth utility function, avoiding curriculum-induced covariate shift.
result SAMPLR preserves optimality under ground-truth distribution, promoting robustness across various environments.
Recent variants improve knowledge distillation performance.
problem Improving the performance of knowledge distillation.
method Introducing additional components or changing the learning process.
result These variants have shown promising results.
Training neural networks is traditionally done by providing a sequence of random mini-batches sampled uniformly from the entire training data. In this work, we analyze the effect of curriculum learning, which involves the non-uniform sampling of mini-batches, on the training of deep networks, and specifically CNNs trai…
New algorithm outperforms existing ones by focusing on mastering rate.
problem Low sample efficiency in learning progress-based algorithms.
method Proposes a new algorithm based on mastering rate.
result Significantly outperforms learning progress-based algorithms.
Proposes a new curriculum learning approach to improve deep RL agent generalization.
problem Challenges in training deep RL agents to generalize over unseen situations.
method Two-stage curriculum learning approach: teacher learns high-exploration curriculum, distills priors to generate expert curriculum.
result 50% improvement in average performance over state-of-the-art methods.
RLVR training dynamics reveal an implicit curriculum that shapes learning progression.
problem Understanding how RLVR overcomes the long-horizon barrier.
method Developed a theory of training dynamics for RLVR on transformers, using Fourier analysis on finite groups.
result Mixed-difficulty training naturally follows an implicit curriculum, shaping the learning progression from easy to hard.
Despite the significant advances in recent years, Generative Adversarial Networks (GANs) are still notoriously hard to train. In this paper, we propose three novel curriculum learning strategies for training GANs. All strategies are first based on ranking the training images by their difficulty scores, which are estima…
Extracting a curriculum from a teacher network improves distillation efficiency.
problem Efficiently training a small network using a large teacher network's output.
method Random projection of teacher network's hidden representations to progressively train the student network.
result Extracted curriculum significantly outperforms one-shot distillation and achieves similar performance to progressive distillation.
RLVR learning dynamics naturally create an implicit curriculum for transformers.
problem How rewards based on final outcomes help overcome the long-horizon barrier in reasoning models.
method Developed a theory of training dynamics for RLVR on transformers, using Fourier analysis on finite groups.
result Mixed-difficulty training induces an implicit curriculum that shapes the learning progression from easy to hard.
We introduce Mix&Match (M&M) - a training framework designed to facilitate rapid and effective learning in RL agents, especially those that would be too slow or too challenging to train otherwise. The key innovation is a procedure that allows us to automatically form a curriculum over agents. Through such a curriculum …
Deep neural networks (DNNs) have great expressive power, which can even memorize samples with wrong labels. It is vitally important to reiterate robustness and generalization in DNNs against label corruption. To this end, this paper studies the 0-1 loss, which has a monotonic relationship with an empirical adversary (r…
Overparameterisation can limit the benefits of curriculum learning in neural networks.
problem The ineffectiveness of curriculum learning in deep learning applications.
method Analytical study connecting curriculum learning and overparameterisation in an online learning setting for a 2-layer network in the XOR-like Gaussian Mixture problem.
result High degree of overparameterisation can limit the benefit from curricula.
Syllabuses for curriculum learning have been developed on an ad-hoc, per task basis and little is known about the relative performance of different syllabuses. We identify a number of syllabuses used in the literature. We compare the identified syllabuses based on their effect on the speed of learning and generalizatio…
Proposes a hierarchical curriculum loss to improve model accuracy and interpretability.
problem Flat label spaces in classification algorithms fail to capture dependencies in real-world data.
method Introduces hierarchical curriculum loss with two properties: satisfying hierarchical constraints and providing non-uniform label weights.
result The proposed loss function significantly outperforms multiple baselines on real-world image datasets.
Teaches uncertainty in ML through practical examples.
problem Lack of uncertainty teaching in ML curricula.
method Developed a curriculum and use cases.
result Motivates adoption of uncertainty concepts in AI courses.
Curriculum Learning - the idea of teaching by gradually exposing the learner to examples in a meaningful order, from easy to hard, has been investigated in the context of machine learning long ago. Although methods based on this concept have been empirically shown to improve performance of several learning algorithms, …
SAT improves adversarial training by smoothing the loss landscape through curriculum learning.
problem Adversarial training sacrifices clean accuracy for robustness and suffers from large generalization error.
method SAT uses curriculum learning to smooth the adversarial loss landscape, improving both clean and robust accuracy.
result SAT models improve clean and robust accuracy significantly compared to adversarial training and other baselines.
This paper introduces CENIE to quantify environment novelty for better UED.
problem Challenges in measuring environment novelty for effective UED.
method CENIE framework using state-action space coverage and Gaussian Mixture Models.
result CENIE improves UED performance across multiple benchmarks.
Curriculum learning has been successfully used in reinforcement learning to accelerate the learning process, through knowledge transfer between tasks of increasing complexity. Critical tasks, in which suboptimal exploratory actions must be minimized, can benefit from curriculum learning, and its ability to shape explor…
By simulating the easy-to-hard learning manners of humans/animals, the learning regimes called curriculum learning~(CL) and self-paced learning~(SPL) have been recently investigated and invoked broad interests. However, the intrinsic mechanism for analyzing why such learning regimes can work has not been comprehensivel…
A method for setting up an automatic curriculum for reinforcement learning tasks.
problem Improving sample efficiency in multi-task reinforcement learning.
method Propose a goal proposal module that prioritizes goals maximizing epistemic uncertainty of the Q-function.
result Significant performance gains over current methods in 13 multi-goal robotic tasks and 5 navigation tasks.
Dropout is a very effective way of regularizing neural networks. Stochastically "dropping out" units with a certain probability discourages over-specific co-adaptations of feature detectors, preventing overfitting and improving network generalization. Besides, Dropout can be interpreted as an approximate model aggregat…
A new method for robot manipulation tasks using imagined object goals.
problem Learning robot manipulation in sparse reward environments.
method Train objects to reach target positions, then use predictions to create a curriculum of tasks.
result Higher success rates in challenging learning scenarios compared to alternatives.
The paper explores how different network architectures learn logical functions under GOTU, finding that a min-degree-interpolator is learned.
problem Learning logical functions with a focus on generalization on the unseen.
method Study of different network architectures trained by SGD under GOTU.
result For sparse functions and certain network models, a min-degree-interpolator is learned on the unseen.