Algorithm learns goals without rewards, controls environments.
problem Learning control without supervised rewards.
method Dual optimization of policy and reward function.
result Agent learns to achieve goals in diverse domains.
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “deepmind lab”
A method to learn multiple Atari games with a single agent.
problem Balancing multiple tasks in reinforcement learning.
method Adaptive task contribution to learning dynamics.
result Single agent surpasses human performance on 57 Atari games.
Paper proposes a new method for efficient exploration in reinforcement learning.
problem Sparse reward reinforcement learning challenges in exploration.
method Learn separate intrinsic and extrinsic task policies, schedule between them, and use successor feature control (SFC).
result Substantially improved exploration efficiency with SFC and hierarchical usage of intrinsic drives.
New unsupervised learning task improves RL performance.
problem Reward-driven feature learning limitations in RL from images.
method Introduce Augmented Temporal Contrast (ATC) for unsupervised learning of image representations.
result Training encoders using ATC matches or outperforms end-to-end RL in most environments.
Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new multi-stage RL agent, …
Flatland is a simple 2D environment for reinforcement learning.
problem Testing and prototyping reinforcement learning agents.
method Simple, lightweight, customizable environment with physical properties.
result Baseline reinforcement learning agents can solve a navigation task in Flatland.
Randomized neural networks improve deep RL agents' generalization.
problem Deep RL agents struggle to generalize to new, semantically similar environments.
method Introduce a randomized (convolutional) neural network to perturb input observations.
result Significantly outperforms various regularization and data augmentation methods.
New approach handles stochastic and partially-observable environments using discrete autoencoders and Monte Carlo tree search.
problem Challenges in planning for stochastic and partially-observable environments.
method Uses discrete autoencoders and a stochastic variant of Monte Carlo tree search.
result Significantly outperforms MuZero on stochastic chess and scales to DeepMind Lab.
SEED RL accelerates deep RL training on modern accelerators.
problem Training deep RL agents on large datasets at high speeds and low cost.
method Centralized inference, IMPALA/V-trace, R2D2, modern accelerators.
result Significant cost reduction and state-of-the-art performance on various games.
CURL uses contrastive learning to improve reinforcement learning performance.
problem Improving reinforcement learning performance on complex tasks.
method Contrastive learning to extract high-level features from raw pixels, followed by off-policy control.
result CURL outperforms prior methods on DeepMind Control Suite and Atari Games.
SLM Lab is a framework for reproducible RL research with modular algorithms.
problem Reproducibility in deep reinforcement learning.
method Modular software framework for RL algorithms, synchronous/asynchronous execution, hyperparameter search, result analysis.
result Comprehensive benchmark and novel RL algorithms (e.g., discrete-AC variant, hybrid training method).
MedGCN uses graph convolutional networks to recommend medications and estimate lab tests.
problem Automatically recommend medications and estimate lab tests for cost savings and better patient care.
method Integrates heterogeneous graph relations, learns node embeddings with graph convolutional networks, and uses cross regularization for multi-task learning.
result MedGCN outperforms state-of-the-art models in both medication recommendation and lab test imputation on real-world datasets.
GAN Lab helps non-experts learn GANs through interactive visualization.
problem Teaching complex deep learning models like GANs to non-experts.
method Interactive visualization tool integrating model structure and training dynamics.
result Users can interactively train and visualize GANs, understanding training dynamics.
Introduces an artificial cyber lab to test and identify cyber resilience measures.
problem Systemic cyber risks and their control methods.
method Classical contagion models and artificial cyber lab simulations.
result Identified two classes of measures: security- and topology-based interventions.
Bayesian nonparametric LABS model adapts to function smoothness in Besov spaces.
problem Estimating functions with unknown smoothness in Besov spaces.
method Lévy Adaptive B-spline (LABS) regression model with automatic smoothness adaptation.
result LABS posterior contracts around true function in Besov classes at nearly minimax-optimal rates.
Method scales up ML science by measuring multiple molecules at once.
problem Scaling up ML-driven science with wet lab experiments.
method Neural extension of compressed sensing for function space.
result Proves orders-of-magnitude gains in information density.
Study compares crowdsourcing with lab experiments using comparison-based psychophysics.
problem Improving data quality in crowdsourcing psychophysics experiments.
method Comparison-based psychophysics, machine learning for triplet prediction.
result Accuracy of crowdsourcing psychophysics close to lab experiments.
Deep RL algorithms can overfit to early experiences, leading to poor performance.
problem Overfitting to early interactions in deep reinforcement learning.
method Proposed a mechanism to periodically reset part of the agent to mitigate overfitting.
result Periodic resetting improves performance in both discrete and continuous action domains.
Embeddings of lab test codes improve mortality prediction and preserve ordinality.
problem Improving mortality prediction using lab test embeddings.
method Training embeddings for LOINC codes and their concatenations with abnormality symbols, evaluating performance on mortality prediction tasks.
result Embeddings of lab test codes improve mortality prediction and preserve ordinality.
Symmetry augmentation speeds up learning in robotics tasks.
problem Learning efficiency in robotics tasks with limited data.
method Data augmentation using symmetry in the quadruped domain of DeepMind control suite.
result Agent learns faster with augmented symmetry experiences.
Deep GNNs and self-supervision boost graph learning at scale.
problem Efficiently deploying GNNs at large scale remains challenging.
method Two large-scale GNNs: a deep transductive node classifier and a very deep inductive graph regressor.
result Award-level performance on MAG240M and PCQM4M benchmarks.
In this paper, we present a new task that investigates how people interact with and make judgments about towers of blocks. In Experiment~1, participants in the lab solved a series of problems in which they had to re-configure three blocks from an initial to a final configuration. We recorded whether they used one hand …
New method trains deep ResNets without normalization, achieving state-of-the-art performance.
problem Training deep ResNets without normalization layers leads to instability and lower accuracy.
method Adaptive gradient clipping and Normalizer-Free ResNets design.
result Normalizer-Free ResNets achieve 86.5% top-1 accuracy on ImageNet, matching EfficientNet-B7.
New method QMLE performs well in complex action spaces without policy gradients.
problem Why policy gradients outperform action-value methods in complex action spaces.
method QMLE framework for action-value methods based on three principles.
result QMLE performs comparably to policy gradient methods in complex action spaces.
Learning the Joint Representation of Heterogeneous Temporal Events for Clinical Endpoint Predictioncs.AI
The availability of a large amount of electronic health records (EHR) provides huge opportunities to improve health care service by mining these data. One important application is clinical endpoint prediction, which aims to predict whether a disease, a symptom or an abnormal lab test will happen in the future according…
RAD enhances RL algorithms with data augmentations.
problem Challenges in RL learning from visual observations.
method RAD is a simple plug-and-play module for RL algorithms.
result RAD improves data-efficiency and final performance.
Deep RL optimizes lab test scheduling for better patient outcomes and cost savings.
problem Redundant lab tests lead to cost and patient discomfort.
method Deep reinforcement learning for optimal scheduling.
result Deep RL policy outperforms heuristic scheduling in both accuracy and cost.
In the present work we are going to give a formal exposition of the ribbon graphs topic based on notes of Labourie \cite{Lab}, since is difficult to find as such in the literature.
This study measures price risk aversion using indirect utility functions in a lab experiment.
problem Measuring risk aversion with uncertain prices in experimental economics.
method Using indirect utility functions and a multiple price list method in a lab experiment.
result Price risk aversion is statistically greater than payoff risk aversion.
Enhanced kernel ridgeless regression improves performance with LAB RBF kernels.
problem Lack of flexibility in kernel ridgeless regression.
method Locally-Adaptive-Bandwidths (LAB) RBF kernels and kernel learning techniques.
result Functions learned from LAB RBF kernels belong to an integral space of RKHSs, demonstrating robust generalization.
Residual algorithms improve reinforcement learning performance.
problem Distribution mismatch in model-based planning.
method Bidirectional target network technique for residual algorithms.
result Residual reinforcement learning significantly outperforms vanilla methods.
This paper explores adversarial training limits and improves model robustness against norm-bounded perturbations.
problem Understanding and improving adversarial robustness of deep neural networks.
method Systematic study of adversarial training with various factors, including model size, activation functions, and unlabeled data.
result Training robust models that go beyond state-of-the-art results by combining larger models, Swish/SiLU activations, and model weight averaging.
Enhances detection of adverse drug events using diverse healthcare record data.
problem Detecting adverse drug events from mixed data types in electronic health records.
method Aggregate diagnosis codes, drug codes, and lab measurements; use recursive feature selection.
result Significant improvement in AUC using additional features, statistically significant.
Accelerates Q-learning by updating targets more efficiently.
problem Improving convergence speed in Q-learning algorithms.
method Proposes an accelerated target update scheme based on momentum methods.
result The proposed algorithms converge faster than vanilla Q-learning.
Algorithm estimates COVID-19 cases from phone calls.
problem Delay in confirming COVID-19 cases.
method Modeling calls as background plus signal, fitting data with high .
result Algorithm estimates cases days before lab results.
A new method, Count-MORL, improves offline reinforcement learning by using state-action frequency.
problem Improving offline reinforcement learning performance.
method Integrates count-based conservatism into model-based offline reinforcement learning.
result The learned policy is near-optimal and outperforms existing methods.
Tracr compiles programs into transformer models for interpretability.
problem Uncertainty in understanding transformer model outputs due to unknown learned programs.
method Tracr compiles human-readable programs into known structure transformer models.
result Known structure of Tracr-compiled models serves as ground-truth for interpretability.
PGMax: Factor Graphs for Discrete Probabilistic Graphical Models and Loopy Belief Propagation in JAXcs.LG
PGMax automates PGM inference on GPUs, improving quality and speed.
problem Efficient inference in complex discrete PGMs.
method Factor graph specification and loopy belief propagation in JAX.
result Higher-quality inference with up to 3x speedups.
Team MIE-Lab forecasts city traffic using past hour's multi-channel images.
problem Predict city-wide traffic status within 15 mins using past hour's multi-channel images.
method Evaluated network architectures, analyzed data, considered spatio-temporal context.
result Best submission in IARAI competition traffic4cast.
Improved scaffold generation for protein motifs using SE(3) flow matching.
problem Lack of structural diversity in generated scaffolds for protein motifs.
method Extended FrameFlow for motif-scaffolding with motif amortization and motif guidance.
result 2.5 times more designable and unique motif-scaffolds compared to state-of-the-art.
New model detects crying in real-world settings with improved accuracy.
problem Generalization of cry detection models to real-world environments.
method Evaluated machine learning approaches on a novel dataset of real-world infant crying.
result Improved F1 score of 0.613 for crying event recognition in real-world settings.
Proposes using entity embedding vectors to improve Gaussian Process models for knowledge transfer across cell lines.
problem Lack of reuse of experimental data for predicting novel processes.
method Hybrid Gaussian Process models with entity embedding vectors to represent product identity.
result Improved performance in predicting novel processes compared to traditional methods.
Robotic clothing manipulation improved with fashion image analysis techniques.
problem Automated identification of clothing categories and landmarks for robotic tasks.
method Training data augmentation methods and rotation invariant convolutions.
result Our approach outperforms state-of-the-art models on unseen datasets.
Improved Zero learning framework wins games like Hex and Havannah.
problem Improving Zero learning for board games with limited resources.
method Fully convolutional structure, global pooling, and checkpointing.
result Won against strong humans in Hex and Havannah.
Proposes a new Deep Recurrent Double Q-Learning model for Atari games.
problem Improving Deep Reinforcement Learning models for Atari games.
method Integrates Double Q-Learning and Recurrent Networks (LSTM, DRQN) for Atari games.
result Demonstrates improved performance in Atari games compared to existing models.
The paper revisits classical competition theory to explain speculative asset price dynamics.
problem Understanding the dynamics of speculative asset prices and their volatility.
method Specialized classical model of competition with reservation prices, incorporating speculation.
result The model explains excess, fat-tailed, and clustered volatility in speculative asset prices.
Deep learning improves reinforcement learning in video games.
problem Challenges in reinforcement learning with high-dimensional inputs.
method Used deep Q-network and batch normalization to improve reinforcement learning.
result Some agents learned to play T-rex Runner better than human experts.
Engine predicts real-time air quality with high resolution.
problem Real-time prediction of air pollutants for health monitoring.
method Combines official data, models, land cover, traffic data for high-resolution predictions.
result Engine produces predictions with resolution of a few dozen meters.