Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to errors introduced by extrapolation, standard off-policy deep reinforcement learn…
On-device research index
arXiv research
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “fixed-batch learning”
This work evaluates task-agnostic exploration methods for fixed-batch learning.
problem Expensive real-world experience for robotics tasks.
method Fixed datasets for arbitrary task learning.
result Improved offline learning for robotics tasks.
Training deep neural networks with Stochastic Gradient Descent, or its variants, requires careful choice of both learning rate and batch size. While smaller batch sizes generally converge in fewer training epochs, larger batch sizes offer more parallelism and hence better computational efficiency. We have developed a n…
A simple approach to offline RL without additional complexity.
problem Learning from a fixed dataset of actions with value estimation errors.
method Adding a behavior cloning term to the policy update of an online RL algorithm and normalizing the data.
result Matches the performance of state-of-the-art offline RL algorithms with minimal changes.
New algorithm learns optimal policy with multi-step lookahead information.
problem Learning optimal policy in reinforcement learning with multi-step lookahead information is NP-hard.
method Adaptive batching policies that process lookahead in state-dependent chunks.
result Order-optimal regret bounds up to a constant factor of lookahead horizon.
New online algorithms tackle dynamic decision-focused learning.
problem Dynamic decision-focused learning in evolving environments.
method Regularization and perturbation techniques for non-convex optimization.
result First provable guarantees for online decision-focused learning.
Develops a new method for efficient stochastic bilevel optimization.
problem Stochastic bilevel optimization problems in machine learning applications.
method Single-Timescale stochAstic BiLevEl optimization (STABLE) method.
result Achieves the same order of sample complexity as stochastic gradient descent for single-level optimization.
Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where collecting data is expensive, and models must be tested offline before being dep…
Improved TD learning reduces batch sampling error.
problem TD learning can be inaccurate in batch settings due to action weighting.
method Introduced PSEC-TD(0) to correct action weighting using importance sampling.
result PSEC-TD(0) produces more accurate value function estimates.
BCPO optimizes offline RL policies by converting uncertainty into conservative bounds.
problem Offline RL's fragility under distribution shifts and model errors.
method Bayesian approach with credible lower bounds and KL regularization.
result BCPO yields an uncertainty-calibrated policy that avoids exploiting model errors.
We propose a new integrated method of exploiting model, batch and domain parallelism for the training of deep neural networks (DNNs) on large distributed-memory computers using minibatch stochastic gradient descent (SGD). Our goal is to find an efficient parallelization strategy for a fixed batch size using process…
A new algorithm learns policies from batch data in hierarchical RL.
problem Learning policies from fixed batches of data without full exploration.
method Modeling RL as a two-player game with a leader-follower structure, proposing StackelbergLearner.
result StackelbergLearner achieves competitive performance in batch RL and real-world datasets.
This research explores discrete diffusion models for natural language generation.
problem Challenges in applying diffusion models to discrete data, especially natural language.
method Investigates Discrete Denoising Diffusion Probabilistic Model (D3PM) and compares it with autoregressive models.
result Discrete diffusion models achieve better processing speed than autoregressive models.
New method improves likelihood-free parameter estimation in complex models.
problem Estimating parameters in simulation-based models with unknown likelihood.
method Nested multi-time-scale stochastic approximation (NMTS) method.
result Eliminates bias and accelerates convergence in likelihood-free inference.
The paper refines and extends batched kernelized bandits, improving regret bounds and introducing a robust setting.
problem Optimizing black-box functions with noisy batches in Reproducing Kernel Hilbert Space.
method Refined and extended existing regret bounds, including adaptive batch sizes and robust optimization.
result Improved regret bounds for batched kernelized bandits, showing optimal number of batches and adaptive batch sizes.
Meta-learning adapts models for unseen tasks across AI, robotics, and NLP.
problem Adapting models to unseen tasks efficiently and accurately.
method Black-box, metric-based, layered, and Bayesian approaches.
result Meta-learning enhances model generalization and adaptation to unseen tasks.
Meta-learning improves neural networks by adapting learning algorithms.
problem Conventional AI approaches solve tasks from scratch, but meta-learning aims to improve the learning algorithm.
method Meta-learning adapts a learning algorithm based on multiple learning episodes.
result Meta-learning can tackle deep learning challenges like data and computation bottlenecks.
Survey explores how transfer learning improves deep reinforcement learning.
problem Challenges in reinforcement learning efficiency and effectiveness.
method Categorizes and analyzes transfer learning approaches.
result Transfer learning enhances reinforcement learning performance.
Machine learning models adapt to motor learning but face challenges.
problem Adapting machine learning to handle motor variability and differentiate new movements from known ones.
method Parameter adaptation, transfer and meta-learning, reinforcement learning.
result Challenges in applying machine learning models for motor learning support systems.
New method uses bi-level optimization to learn useful representations for imitation learning.
problem Learning useful representations for multiple tasks in imitation learning settings.
method Formulates representation learning as a bi-level optimization problem.
result Bi-level optimization framework provides sample complexity benefits for imitation learning.
Tabular Q-Learning with learned state abstractions solves continuous control tasks.
problem Challenging reinforcement learning problems in continuous control.
method Learned state abstraction to transform continuous state-space into discrete.
result Tabular Q-Learning with learned abstractions achieves efficient learning in unseen tasks.
Study Whittle index learning algorithms for restless bandits with constant stepsizes.
problem Optimizing decisions in restless multi-armed bandits with constant stepsizes.
method Developed Q-learning algorithms with constant stepsizes for index learning in restless bandits, extending to DQN and function approximations.
result The algorithms learn the Whittle index effectively.
Paper discusses flaws in traditional RL for lifelong learning.
problem Traditional RL fails to model lifelong learning systems.
method Simplified prototype of lifelong RL system.
result Insights into lifelong RL, showing traditional RL's limitations.
AI learns to learn sequentially without forgetting.
problem Preventing catastrophic forgetting in machine learning models.
method Meta-learning a neuromodulatory activation-gating function to control selective activation in deep neural networks.
result State-of-the-art continual learning performance with 600 classes (9,000 updates).
Poisson learning doesn't solve graph semi-supervised learning issues.
problem Global information loss in graph-based semi-supervised learning.
method Poisson learning is Laplace regularization with thresholding.
result Poisson learning cannot overcome the global information loss problem.
New unsupervised learning technique learns independent kernels for better machine learning tasks.
problem Improving unsupervised representation learning for machine learning tasks.
method Stacking convolutional transforms using alternating proximal minimization scheme.
result DCTL outperforms shallow version CTL on benchmark datasets.
Meta-learning helps models learn quickly from few samples.
problem Deep learning requires many samples, which are hard to get.
method Meta-learning optimizes models to adapt quickly to new tasks.
result Meta-learning can improve model efficiency and adaptability.
New self-imitation learning method improves performance in continuous control tasks.
problem Improving off-policy learning in continuous control tasks.
method Proposes a n-step lower bound to generalize lower-bound Q-learning and introduces a new family of self-imitation learning algorithms.
result n-step lower bound Q-learning achieves a better trade-off between bias and contraction rate, leading to improved performance.
Deep reinforcement learning finds optimal learning policies for adaptive systems.
problem Finding individualized learning plans for learners with unknown latent traits.
method Formulated as a Markov decision process, applied deep Q-learning with a transition model estimator.
result The algorithm efficiently discovers optimal learning policies with small data sets.
Unified framework explains all types of learning, including brain.
problem Lack of clear explanation for deep learning success.
method Constructing a learning principle that equates all learning to probability estimation.
result Unified understanding of learning across different fields.
Cyclical learning rates improve DRL performance without manual tuning.
problem Manual hyperparameter tuning in DRL is time-consuming and error-prone.
method Proposes cyclical learning rates for DRL problems.
result Cyclical learning achieves similar or better results than fixed learning rates.
PAC Bounds for Imitation and Model-based Batch Learning of Contextual Markov Decision Processescs.LG
Study batch reinforcement learning methods for personalized medical treatments.
problem Batch reinforcement learning for personalized medical treatments.
method Direct policy learning and model-based learning approaches.
result Model-based learning is impossible with finite model classes but feasible with relaxed conditions.
A new meta-meta classification method tackles few-shot learning tasks.
problem Learning with limited data in small-data settings.
method Designing an ensemble of learners for a large set of problems, then learning how to combine them for a new problem.
result Meta-meta classification outperforms traditional meta-learning and ensembling approaches in one-shot learning tasks.
The paper proposes a learning algorithm that improves adaptability and generalization.
problem Improving adaptability and generalization in learning models.
method Learning to meta-learn by meta-finetuning on related tasks before adapting to specific tasks.
result Learning to meta-learn improves adaptability and generalization across various tasks.
This paper surveys meta-learning, online, and continual learning.
problem Combining and understanding meta-learning, online, and continual learning.
method Organizing various problem settings using consistent terminology and formal descriptions.
result Fosters further advancements in meta-learning, online, and continual learning.
Relational logistic regression (RLR) is a representation of conditional probability in terms of weighted formulae for modelling multi-relational data. In this paper, we develop a learning algorithm for RLR models. Learning an RLR model from data consists of two steps: 1- learning the set of formulae to be used in the m…
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.
Contrastive learning works well with redundant data views.
problem Improving unsupervised learning with redundant data views.
method Theoretical analysis of contrastive learning in a multi-view setting.
result Linear functions of learned representations are nearly optimal on prediction tasks when views are redundant.
Paper analyzes iterative learning for concept classes and learns half-spaces.
problem Learning concept classes efficiently with iterative learners.
method Analyzes various settings of iterative learning and provides a constructive algorithm for half-spaces.
result Constructive iterative algorithm for learning half-spaces from informant.
This paper introduces Dex, a reinforcement learning environment toolkit specialized for training and evaluation of continual learning methods as well as general reinforcement learning problems. We also present the novel continual learning method of incremental learning, where a challenging environment is solved using o…
Bayesian approach adapts deep network structure for continual learning.
problem Training neural networks with sequential or streaming tasks.
method Bayesian approach to learn deep network structure for each task.
result Model performs comparably or better than recent advances in continual learning.
Cliff-Learningcs.LG
Study shows cliff-learning in transfer learning from foundation models.
problem Data-scaling of transfer learning from foundation models in low data regimes.
method Investigation of cliff-learning phenomenon through foundation-model analysis and toy models.
result Cliff-learning reflects compatibility between priors and tasks.
Meta-strategy learns tuning parameters for online learning methods.
problem Difficulty in setting tuning parameters for online learning methods.
method Meta-learning approach to learn parameters from past tasks.
result Meta-strategy improves on learning each task in isolation.
This article reviews statistical methods for learning data representations.
problem Learning meaningful representations of data.
method Statistical perspective on unsupervised and supervised representation learning.
result Recent advances in representation learning from a statistical viewpoint.
We discuss a general method to learn data representations from multiple tasks. We provide a justification for this method in both settings of multitask learning and learning-to-learn. The method is illustrated in detail in the special case of linear feature learning. Conditions on the theoretical advantage offered by m…
Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, which poses a significant challenge in some scenarios. A promising altern…
Machine can learn its own bias from related tasks.
problem Machine learning bias through hand-crafted features.
method Introduces two models: PAC-based and hierarchical Bayes.
result Machine can learn bias from multiple tasks.
This paper aims to define out-of-distribution learning.
problem Lack of formal definitions for out-of-distribution learning.
method Chronological approach using PAC learning framework.
result Established a universally agreed-upon approach to quantify different types of learning.