This work tackles long-term visual planning by goal-conditioned hierarchical predictors.
problem Current learning approaches fail on long-horizon tasks due to lack of goal information and coarse-to-fine planning.
method Formulate goal-conditioned predictors (GCPs) and hierarchical models to predict trajectories between observations.
result GCPs enable effective long-term planning with much longer horizons than before.
Generative model learns goal-directed visual plans from raw data.
problem Learning goal-directed visual plans from high-dimensional observations.
method Combines representation learning and planning, maximizing mutual information.
result Generative model learns low-dimensional representation explaining causal data.
Hierarchical Foresight improves robot vision tasks by planning long-term goals.
problem Compounding uncertainty and scalability issues in long horizon video prediction.
method Subgoal generation and planning using hierarchical visual foresight (HVF).
result Achieves nearly 200% performance improvement in vision-based manipulation tasks.
LEAPS uses semantic models to improve reinforcement learning in diverse environments.
problem Generalizing and adapting to unseen environments in reinforcement learning.
method Hybrid model-based and model-free approach with a multi-target sub-policy and a Bayesian semantic model.
result LEAPS outperforms baselines in visual navigation tasks using diverse indoor scenes.
MuZero visualizes its internal representations to stabilize planning.
problem Stability issues in MuZero's planning process.
method Visualized MuZero's latent representations and proposed regularization techniques.
result Action trajectories diverge between observation embeddings and internal state transitions, leading to instability.
This work learns visual representations for deformable objects using contrastive estimation.
problem Challenges in learning plannable visual representations for deformable objects.
method Jointly optimizes visual representation and dynamics models using contrastive estimation.
result Substantial improvements in performance over standard model-based learning techniques.
Few-shot goal learning for robot tasks from a few examples.
problem Learning objectives for robot tasks from limited examples.
method Meta-learning a classifier to recognize new goals from a few examples.
result Meta-learning approach can be applied to both reinforcement learning and visual planning.
New approach for obstacle avoidance in robotics using learned representations.
problem Challenges in sensor-based motion planning for new and dynamic environments.
method Proposes a new obstacle representation using PointNet architecture trained jointly with policies for obstacle avoidance.
result Significant improvements in accuracy and efficiency compared to state of the art.
A key challenge in complex visuomotor control is learning abstract representations that are effective for specifying goals, planning, and generalization. To this end, we introduce universal planning networks (UPN). UPNs embed differentiable planning within a goal-directed policy. This planning computation unrolls a for…
This work proposes a RL approach to learn versatile robotic manipulation tasks.
problem Challenging manipulation tasks in robotics and vision.
method Reinforcement learning (RL) to combine primitive skills, no intermediate rewards, few demonstrations, and efficient skill learning.
result Versatile robotic manipulation in challenging settings with temporary occlusions and dynamic scene changes.
The study uses machine learning to analyze office floor plans and predict function based on geometry.
problem Lack of formalisms to describe spatial affordance in automated floor-plan generation tools.
method Supervised and unsupervised data mining techniques, including J48 algorithm, were used to analyze office floor plans.
result J48 algorithm can predict class performance on unseen examples up to 79.5% for office dataset.
Regularizes model-based planning using energy-based models for efficient learning.
problem Challenges in using learned dynamics models for accurate planning.
method Regularization using energy estimates of state transitions.
result Proposes effective regularization method for planning with pre-trained dynamics models.
Explains curves and surfaces in differential geometry.
problem Understanding smooth curves and surfaces in differential geometry.
method Problem-centered, elementary, visual approach focusing on essential techniques.
result Provides a solid foundation for further study in differential geometry.
The paper uses deep learning to speed up spatial and visual connectivity analysis.
problem Slow calculation of spatial and visual connectivity metrics.
method Investigates machine learning models and a pipeline for training them on spatial and visual connectivity analysis.
result Deep learning models significantly speed up the analysis process.
These notes introduce key techniques in differential geometry for curves and surfaces.
problem Understanding the basics of differential geometry for curve and surface analysis.
method Problem-centered, elementary, visual approach to teaching essential techniques.
result Provides a solid foundation for further study in differential geometry.
Study uses U-Net for efficient urban planning map semantic segmentation.
problem Manual visual interpretation of urban planning maps is inefficient and time-consuming.
method Utilized U-shape fully convolutional architecture for end-to-end semantic segmentation.
result Achieved high Jaccard similarity coefficient of 93.63% and overall accuracy of 99.36%.
Agent learns to navigate uncertain 3D maps using a hybrid planner.
problem Planning in 3D environments with uncertain topological maps.
method Hierarchical strategy combining graph planner and local policy, data-driven learning with neural network.
result Machine learning can overcome missing information in probabilistic topological maps.
Sabrina integrates financial data and domain knowledge for better visualization.
problem Scattered financial data across various sources makes it hard for analysts to understand the economy.
method Sabrina uses a pipeline to fuse firm-specific and macroeconomic data, visualizing it in a unified interface.
result Sabrina aids financial analysts in their analysis process, as shown in a user study.
MuZero learns models to master complex games without domain knowledge.
problem Mastering complex, real-world domains with unknown dynamics.
method Combining tree-based search with learned models.
result Achieves superhuman performance in diverse domains.
Deep network predicts action sequences for complex tasks from a scene image.
problem Scalable task and motion planning from initial scene images.
method Deep convolutional recurrent neural network that predicts action sequences.
result Predicts promising action sequences, reducing motion planning problems.
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.
KeyIn discovers keyframes to simplify video analysis.
problem Extracting essential dynamics from videos interleaved with predictable details.
method A hierarchical Keyframe-Inpainter (KeyIn) model learns keyframes and fills in the rest.
result KeyIn finds informative keyframes across various video dynamics.
Director learns hierarchical behaviors from pixels, outperforming exploration methods.
problem Challenges in learning long-term hierarchical behaviors from pixels.
method Directly learns hierarchical behaviors from pixels using a latent space world model.
result Director outperforms exploration methods on various tasks.
Agents learn action spaces from observation alone.
problem Learning an agent's action space from visual observation.
method Stochastic video prediction and composable action representations.
result Learned representations disentangle action structure.
Proposes DLGPD model to learn dynamics from images for planning.
problem Planning in unknown, indirectly observable environments.
method Deep latent Gaussian process dynamics model trained jointly with neural networks.
result Demonstrates improved data efficiency and transfer learning.
PLANS synthesizes programs from noisy inputs using neural specs and filtering.
problem Synthesizing robust programs from noisy, raw inputs.
method Hybrid model combining neural extraction and rule-based synthesis with noise filtering.
result State-of-the-art performance in diverse environments with no ground-truth training.
Visualizes movement control optimization landscapes to understand why it's hard and how to make it easier.
problem Understanding and optimizing movement control problems in animation research.
method Novel visualizations of high-dimensional control optimization landscapes.
result Trajectory optimization becomes increasingly ill-conditioned with longer trajectories, while parameterizing control as partial target states can act as an efficient preconditioner.
OP3 models entities for better task generalization in reinforcement learning.
problem Generalizing to unseen physical tasks with combinatorial complexity.
method Object-centric perception, prediction, and planning (OP3) framework.
result OP3 outperforms oracle models and state-of-the-art video prediction models.
Modern reinforcement learning algorithms reach super-human performance on many board and video games, but they are sample inefficient, i.e. they typically require significantly more playing experience than humans to reach an equal performance level. To improve sample efficiency, an agent may build a model of the enviro…
It is well established that humans decision making and instrumental control uses multiple systems, some which use habitual action selection and some which require deliberate planning. Deliberate planning systems use predictions of action-outcomes using an internal model of the agent's environment, while habitual action…
MAOP learns object dynamics from raw visual data.
problem Efficient learning of dynamics from raw visual data for multiple objects.
method Three-level learning architecture with spatial-temporal relational reasoning.
result Significantly outperforms previous methods in sample efficiency and generalization.
SGM combines deep learning and planning for robust long-horizon tasks.
problem Combining deep learning and planning for robust long-horizon tasks.
method Sparse Graphical Memory (SGM) that stores states and feasible transitions in a sparse memory, aggregating states according to a two-way consistency objective.
result SGM significantly outperforms current state of the art methods on long horizon, sparse-reward visual navigation tasks.
We solve 6-DoF localisation and 3D reconstruction using deep state-space models.
problem 6-DoF localisation and dense 3D reconstruction in spatial environments.
method Approximate Bayesian inference in a deep state-space model combining learning and domain knowledge.
result Near state-of-the-art performance on UAV flight data.
Approach detects illegal insider trading proactively from diverse data sources.
problem Detecting illegal insider trading in the stock market.
method Deep-learning and discrete signal processing on time series data, combined with tree-based visualization.
result Approach has a good success rate in detecting illegal insider trading patterns.
The paper proposes a framework to reason about object dynamics for faster reinforcement learning.
problem Current reinforcement learning approaches lack prior knowledge about the environment, limiting efficiency.
method Integrates object dynamics and behavior into reinforcement learning to improve efficiency.
result Demonstrates the need for reasoning about object behavior and dynamics, leading to faster learning.
Adapts DR objectives for both sample and feature size reduction.
problem Simultaneously reduce sample and feature sizes.
method Semi-relaxed Gromov-Wasserstein optimal transport.
result OT plan delivers competitive hard clustering.
Enhances crowd safety through AI and data-driven models.
problem Improving crowd safety during events.
method Innovative data collection, AI, and machine learning.
result Accurate multi-day forecasts for event planning.
C-Learning estimates reachability over time to solve multi-goal tasks.
problem Multi-goal reaching challenges in reinforcement learning.
method Cumulative accessibility functions and recurrence relations.
result Optimal cumulative accessibility functions are monotonic in horizon.
DPN combines model-based and model-free reinforcement learning for efficient planning.
problem Efficiently plan actions in reinforcement learning environments.
method Combines model-based and model-free reinforcement learning, dynamically constructing plans using a learned state-transition model.
result Reduces the number of state transitions during planning by up to 96%, improving data efficiency and performance.
Improves RL planning by proposing sub-goals hierarchically.
problem Sequential planning assumption in RL.
method Divide-and-Conquer Monte Carlo Tree Search (DC-MCTS).
result Improves navigation and control tasks.
New method designs fairer transport plans with uncertainty.
problem Designing fair and balanced mass transport plans.
method Hierarchical fully probabilistic design (HFPD) for transport plans.
result Optimal hyperprior for transport plans with uncertain marginals.
Deep reinforcement learning has been successfully applied to several visual-input tasks using model-free methods. In this paper, we propose a model-based approach that combines learning a DNN-based transition model with Monte Carlo tree search to solve a block-placing task in Minecraft. Our learned transition model pre…
MPNet uses neural networks for efficient motion planning.
problem Exponential increase in computational complexity with motion planning problem dimensionality.
method MPNet encodes workspaces from point cloud measurements and generates collision-free paths.
result MPNet is computationally efficient and generalizes to unseen environments.
3D U-Net improves kidney and tumor segmentation from CT scans.
problem Manual segmentation by clinicians is laborious and error-prone.
method Multi-scale supervised 3D U-Net with deep supervision and post-processing.
result MSS U-Net achieves high Dice coefficients (0.969 for kidney, 0.805 for tumor) on KiTS19 dataset.
We aim to reduce the burden of programming and deploying autonomous systems to work in concert with people in time-critical domains, such as military field operations and disaster response. Deployment plans for these operations are frequently negotiated on-the-fly by teams of human planners. A human operator then trans…
Generative adversarial networks improve radiation therapy planning.
problem Creating optimal radiation therapy plans.
method Using a GAN to predict 3D dose distributions directly.
result Significantly outperforms previous methods in clinical satisfaction and metrics.
SAGDA generates synthetic agricultural datasets to improve ML in African farming.
problem Data scarcity in African agriculture limits machine learning innovations.
method SAGDA is an open-source Python toolkit that generates, augments, and validates synthetic agricultural datasets.
result SAGDA enhances ML applications in agriculture, such as yield prediction and fertilizer recommendation.
Study integrates reliability constraints into generation planning models.
problem Challenges in integrating reliability constraints with generation planning models.
method Leverages a weighted oblique decision tree (WODT) technique to embed reliability verification constraints.
result Demonstrates effectiveness in achieving reliable and optimal planning solutions.