Study benchmarks RL algorithms on real robots, revealing their performance and hyper-parameter sensitivity.
problem Lack of benchmark tasks and source code for reinforcement learning on physical robots.
method Introduced benchmark tasks with multiple robots, tested 4 RL algorithms, analyzed hyper-parameter sensitivity.
result Some RL implementations can be applied to physical robots with proper setup, but hyper-parameters need re-tuning.
Framework uses physics knowledge to improve spatiotemporal prediction with limited data.
problem Challenges in modeling physical systems with limited real-world data.
method Physics-aware meta-learning with auxiliary tasks, incorporating PDE-independent spatial and temporal modules.
result Framework outperforms in spatiotemporal prediction tasks with limited data.
Extends neural network approximations to guarantee continuity of real-world learning tasks.
problem Guaranteeing continuity of real-world learning tasks given by conditional expectations.
method Establishing conditions on learning tasks that guarantee their continuity under a factorization of the data-generating process.
result Conditions guaranteeing the continuity of practically any derived learning task.
We created financial benchmarks for distribution shifts in crude oil prices and volatility.
problem Scarcity of task-labeled time-series benchmarks in finance.
method Transformed asset price data into volatility proxies, generated task labels based on distribution shifts, and made datasets publicly available.
result Inclusion of task labels improves continual learning algorithms' performance on real-world data.
Myriad offers a testbed for integrating machine learning and trajectory optimization.
problem Real-world trajectory optimization challenges.
method JAX-based testbed with machine learning and trajectory optimization integration.
result End-to-end learning and planning with neural ODEs.
VIRTUAL improves federated multi-task learning for non-convex models.
problem Real-world federated datasets show statistical heterogeneity.
method VIRTUAL treats federated network as a star-shaped Bayesian network and uses variational inference.
result VIRTUAL outperforms state-of-the-art for federated learning on real-world datasets.
Mobile network that millions of people use every day is one of the most complex systems in the world. Optimization of mobile network to meet exploding customer demand and reduce capital/operation expenditures poses great challenges. Despite recent progress, application of deep reinforcement learning (DRL) to complex re…
Reinforcement learning is a promising approach to developing hard-to-engineer adaptive solutions for complex and diverse robotic tasks. However, learning with real-world robots is often unreliable and difficult, which resulted in their low adoption in reinforcement learning research. This difficulty is worsened by the …
CCMTL efficiently handles massive number of tasks in regression problems.
problem Handling a massive number of tasks in regression problems.
method Integrates convex clustering with k-nearest neighbor graph and a new optimization method.
result CCMTL outperforms seven state-of-the-art multi-task learning methods in terms of accuracy and efficiency.
Deep learning faces challenges in real-world tasks.
problem Challenges in applying deep learning to novel tasks without existing baselines.
method Case studies from research & development in conjunction with industry.
result Best practices for deep learning in practice.
TOPNet integrates task-based evaluation into machine learning models.
problem Non-differentiable task-based evaluation criteria in real-world applications.
method Task-Oriented Prediction Network (TOPNet) with learnable surrogate loss function.
result TOPNet significantly outperforms traditional and heuristic models in financial prediction tasks.
Study evaluates scalability and real-world impact of disentangled representations.
problem Scalability and real-world impact of disentangled representations.
method New high-resolution dataset and architectures for disentangled representation learning.
result Disentanglement predicts out-of-distribution task performance.
SECRET combines ML and NLP for better real-world task classification.
problem Limited integration of semantic relationships in supervised ML.
method SECRET fuses semantic information from NLP with feature space of supervised ML.
result Up to 14.0% accuracy and 13.1% F1 score improvements over traditional supervised 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.
This paper aims to promote real-world use of DRL in autonomous driving.
problem Challenges in deploying DRL in real-world autonomous driving systems.
method Overview of AD tasks, RL algorithms, and DRL applications; discussion of deployment challenges.
result Challenges to real-world deployment of DRL in AD systems.
Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause proficient but specialized policies to fail at test time. Given that it is impractical …
Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the interaction time with the environment is limited, as is the case for most real-world ro…
Paper tackles AI driving competition challenges with mixed simulation and real-world data.
problem AI algorithms perform poorly in real-world environments compared to simulated ones and vice versa.
method Employed imitation learning on a mixed dataset to train algorithms equally well in all environments.
result Trained algorithms performed well in both simulated and real-world environments.
Method trains vision and control policies on real robots quickly.
problem Training vision-based control policies on real robots efficiently.
method Multi-task Reinforcement Learning with auxiliary tasks.
result Significant learning speed-ups and task learning from-scratch.
Robust CD method for real-world time series with power-law distributions.
problem Challenges in causal discovery due to noise sensitivity.
method Power-law spectral feature extraction for robust CD.
result Consistently outperforms state-of-the-art alternatives on real-world datasets.
A novel Q-learning algorithm connects information theory to MPC, improving control tasks.
problem Combining model-free RL and MPC for real-world systems with expensive queries and uncertain dynamics.
method Developed a Q-learning algorithm that uses entropy regularization and leverages biased models.
result Improves control performance on sim-to-sim tasks compared to optimal control and RL from scratch.
Prototype real-world RL environment for robotics training.
problem Lack of common real-world RL benchmark.
method Developed OffWorld Gym with open access to real-world robotics environments.
result Baseline results in navigation task on real and simulated terrain.
Proposes a method for model-based RL in complex environments without perfect simulators.
problem Lack of cheap and perfect simulators in real-world tasks.
method Induces a world program by learning dynamics and actions in graph-based environments.
result World program enables complex planning tasks in environments without perfect simulators.
A2MT learns agents to select which modalities to acquire at test time.
problem Learning agents to select modalities for multimodal temporal data acquisition.
method Perceiver IO architecture for active acquisition of multimodal temporal data.
result Agents successfully learn cost-reactive acquisition behavior on real-world datasets.
PNA improves GNNs for graph data with multiple aggregators.
problem Capturing continuous features in graph neural networks.
method Combines multiple aggregators with degree-scalers.
result PNA outperforms existing models on graph theory and real-world tasks.
A graph abstraction speeds up reinforcement learning in complex environments.
problem Learning hierarchical reinforcement learning tasks in complex environments.
method Jointly trains a latent pivotal state model and a curiosity-driven policy. Uses a world graph to guide high-level and low-level agents.
result Significant performance and efficiency improvements over baseline methods.
A new framework for robot block-stacking tasks using causal probabilistic models.
problem Robots fail outside controlled environments due to uncertainty and lack of explicit design for all scenarios.
method Causal probabilistic framework combining causal models and probabilistic representations of noise.
result Robots can perceive, reason about, and explain their environment for block-stacking tasks.
RETINA Benchmark evaluates Bayesian deep learning on diabetic retinopathy detection.
problem Reliable uncertainty quantification for deep learning models in medical applications.
method Design and evaluation of a real-world diabetic retinopathy dataset and tasks.
result Benchmarking of Bayesian deep learning methods on diabetic retinopathy detection tasks.
DeepMNE learns multi-network node features for better classification.
problem Learning node features across multiple networks.
method Semisupervised autoencoder for multi-network topology.
result DeepMNE outperforms state-of-the-art methods in node classification.
Deep RL learns robot walking gaits in real-world environments.
problem Difficulty in applying deep RL to real-world robotic tasks due to poor sample complexity and hyperparameter sensitivity.
method Sample-efficient deep RL algorithm based on maximum entropy RL, requiring minimal per-task tuning and modest trials.
result Acquired stable walking gaits on a real-world Minitaur robot in about two hours.
GNNs improve supply chain analytics with real-world benchmarks.
problem Limited research on applying GNNs to supply chain management.
method Conceptual discussions, detailed formulations, examples, mathematical definitions, and task guidelines.
result GNN-based models outperform other methods by 10-40% in various supply chain tasks.
RHPO improves data-efficiency for hierarchical reinforcement learning.
problem High data requirements for general reinforcement learning algorithms in robotics.
method RHPO employs compositional inductive biases and task sharing mechanisms.
result RHPO enables stable and fast learning for complex domains with positive transfer.
The paper proposes a machine learning method to detect drivers' affective states using physiological signals.
problem Detecting and assessing drivers' affective states to improve driving safety and well-being.
method Multiview multi-task machine learning approach using physiological signals.
result Accounting for drive-specific differences significantly improves model performance.
Multi-task learning aims to learn multiple tasks jointly by exploiting their relatedness to improve the generalization performance for each task. Traditionally, to perform multi-task learning, one needs to centralize data from all the tasks to a single machine. However, in many real-world applications, data of differen…
This work shows how to use simulators to learn efficient exploration in real-world RL.
problem Sample complexity of real-world reinforcement learning.
method Coupling exploratory policies learned in simulators with practical approaches.
result Polynomial sample complexity in real world, exponential improvement over direct sim2real transfer.
This work tackles real-world robotic reinforcement learning challenges.
problem Limited success of reinforcement learning in real-world robotics.
method Proposes a system for autonomous real-world learning without instrumentation.
result Demonstrates a complete system that learns without human intervention.
ST-MAML tackles task ambiguity in meta-learning by encoding tasks with stochastic representations.
problem Handling tasks from multiple distributions is challenging for meta-learning due to task ambiguity.
method ST-MAML uses a stochastic neural network module to encode tasks and propagate task representations to revise input variable encoding.
result ST-MAML matches or outperforms state-of-the-art methods on various tasks.
SAC improves deep RL by balancing reward and randomness.
problem High sample complexity and hyperparameter brittleness in RL.
method Maximum entropy framework, constrained optimization, temperature tuning.
result SAC achieves state-of-the-art performance and stability.
Bayesian optimization adapts domain parameters for more robust robot policies.
problem Learning policies for robot control from simulation data often fails in the real world due to the 'reality gap'.
method Bayesian Domain Randomization (BayRn) uses Bayesian optimization to adapt domain parameter distributions during training.
result BayRn achieves better sim-to-real transfer compared to fixed distribution methods.
GLACE embeds large-scale attributed graphs effectively, preserving structure and attributes.
problem Uncertainty and complexity in large-scale attributed graphs.
method Gaussian embeddings for scalable and efficient graph embedding.
result GLACE outperforms state-of-the-art methods on multiple graph analysis tasks.
Hybrid RL combines simulated and real data for robust autonomous flight.
problem Challenges in training deep RL models for real-world robotic tasks.
method Combines real-world and simulated data to improve generalization.
result Quadrotor avoids collisions using only a monocular camera.
New method accelerates MBRL by 10x for complex quadrotor tasks.
problem Inefficient training of world models in MBRL for complex robotic tasks.
method Parallelized state-space models and privileged information for training.
result Significant speedup in world model and MBRL training times.
ptype infers data types robustly in real-world data.
problem Type inference fails with missing data and anomalies.
method Probabilistic robust type inference method.
result Outperforms existing methods.
LSTMs fail in financial tasks, CL improves performance.
problem Financial time-series analysis and inference with LSTMs.
method Continual Learning (CL) approach for financial decision making.
result CL outperforms LSTMs and FFNN in financial decision making.
MTNPs jointly model multiple correlated tasks from various sources.
problem Naive NPs can only model a single stochastic process and infer tasks independently.
method MTNPs are a hierarchical extension of NPs that jointly infer tasks from multiple stochastic processes, considering inter-task correlation and handling incomplete data.
result MTNPs successfully model multiple tasks jointly, discovering and exploiting their correlations in various real-world data.
This work improves AI's ability to solve physical tasks by optimizing world models in abstracted spaces.
problem Developing AI agents capable of solving diverse physical tasks and generalizing to new environments.
method Investigates and optimizes a family of joint-embedding predictive world models (JEPA-WMs) for efficient planning in abstracted spaces.
result Proposes a model that outperforms two established baselines in both navigation and manipulation tasks.
The study evaluates GRL approaches and finds limitations in their applicability.
problem Challenges in applying GRL approaches to real-world graphs with varying structural differences.
method Empirical data-driven framework and theoretical analysis of GRL approaches.
result Existing GRL approaches are insufficient for real-world graphs with diverse structural patterns.
Neural circuit model re-purposed for robotic control tasks.
problem Learning simple robotic control tasks.
method Re-purposing a biological neural circuit model to control robotic tasks using a search-based optimization algorithm.
result Neuronal Circuit Policies (NCPs) perform on par and in some cases surpass contemporary deep learning models with fewer parameters and interpretable dynamics.