A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
RLVR training dynamics reveal an implicit curriculum that shapes learning progression.
RLVR learning dynamics naturally create an implicit curriculum for transformers.
Curriculum learning shows marginal benefits over random ordering on standard datasets.
Extracting a curriculum from a teacher network improves distillation efficiency.
Paper introduces a new curriculum generation method for reinforcement learning.
Analyzes when and why curricula help neural networks learn.
Automatically generates a deep RL curriculum for faster and more stable learning.
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…
Unified framework for multi-objective curriculum learning in robotics.
Curriculum learning speeds up agent learning in Minecraft, a complex visual domain.
New algorithm combines curriculum learning with HER for complex object manipulation tasks.
Curriculum learning and imitation learning improve control over financial time-series data.
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…
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.
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.
Survey on curriculum learning for reinforcement learning.
EPC curriculum improves MARL performance as agent population grows.
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 …
This paper introduces CENIE to quantify environment novelty for better UED.
Bi-directional Curriculum Learning improves graph anomaly detection by considering both homogeneity and heterogeneity.
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-…
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…
CP-DRL improves curriculum reinforcement learning by leveraging causal relationships.
ACL improves DRL by adapting task difficulty to agent's capabilities.
Curriculum learning helps neural networks learn parities more efficiently.
Recent variants improve knowledge distillation performance.
SAMPLR optimizes for ground truth in aleatoric parameters to avoid curriculum-induced covariate shift.
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…
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…
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…
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 …
Proposes a new curriculum learning approach to improve deep RL agent generalization.
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…
New algorithm outperforms existing ones by focusing on mastering rate.
SAT improves adversarial training by smoothing the loss landscape through curriculum learning.
Proposes a hierarchical curriculum loss to improve model accuracy and interpretability.
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, …
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…
Teaches uncertainty in ML through practical examples.
Overparameterisation can limit the benefits of curriculum learning in neural networks.
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…
Goal-oriented reinforcement learning has recently been a practical framework for robotic manipulation tasks, in which an agent is required to reach a certain goal defined by a function on the state space. However, the sparsity of such reward definition makes traditional reinforcement learning algorithms very inefficien…
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.
Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.