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.
Prototype real-world RL environment for robotics training.
Learning to control robots directly based on images is a primary challenge in robotics. However, many existing reinforcement learning approaches require iteratively obtaining millions of robot samples to learn a policy, which can take significant time. In this paper, we focus on learning a realistic world model capturi…
This work tackles real-world robotic reinforcement learning challenges.
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 …
A new framework for robot block-stacking tasks using causal probabilistic models.
RL controls small soccer robots in a real league, beating human-designed policies.
Through many recent successes in simulation, model-free reinforcement learning has emerged as a promising approach to solving continuous control robotic tasks. The research community is now able to reproduce, analyze and build quickly on these results due to open source implementations of learning algorithms and simula…
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…
Robot learns to juggle two balls from 56 minutes of experience.
This work evaluates task-agnostic exploration methods for fixed-batch learning.
Efficient attacks on DRL models without model access and low computation.
Deep reinforcement learning (deep RL) holds the promise of automating the acquisition of complex controllers that can map sensory inputs directly to low-level actions. In the domain of robotic locomotion, deep RL could enable learning locomotion skills with minimal engineering and without an explicit model of the robot…
For a safe, natural and effective human-robot social interaction, it is essential to develop a system that allows a robot to demonstrate the perceivable responsive behaviors to complex human behaviors. We introduce the Multimodal Deep Attention Recurrent Q-Network using which the robot exhibits human-like social intera…
New method improves smoothness of robot learning.
Survey examines challenges and solutions in sim-to-real transfer for robotics.
The combination of deep neural network models and reinforcement learning algorithms can make it possible to learn policies for robotic behaviors that directly read in raw sensory inputs, such as camera images, effectively subsuming both estimation and control into one model. However, real-world applications of reinforc…
Automates decision-making for human operators managing multiple robots.
ROBEL platform accelerates reinforcement learning with low-cost robots.
Mitigates instability in reinforcement learning for safer robotics.
Robots learn to navigate rough terrain using reinforcement learning.
Robot learns from human demonstrations to work autonomously.
Deep reinforcement learning provides a promising approach for vision-based control of real-world robots. However, the generalization of such models depends critically on the quantity and variety of data available for training. This data can be difficult to obtain for some types of robotic systems, such as fragile, smal…
This work shows how to use simulators to learn efficient exploration in real-world RL.
We propose a neural information processing system which is obtained by re-purposing the function of a biological neural circuit model, to govern simulated and real-world control tasks. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce Neuronal Circuit Policies (NCPs), defined as…
Central to robot exploration and mapping is the task of persistent localization in environmental fields characterized by spatially correlated measurements. This paper presents a Gaussian process localization (GP-Localize) algorithm that, in contrast to existing works, can exploit the spatially correlated field measurem…
A new optimizer d-AmsGrad improves deep learning for robot learning in non-stationary problems.
Survey on RL reproducibility using real-world robots.
Paper proposes an end-to-end learning method for state estimation in robotics.
Applications of safety, security, and rescue in robotics, such as multi-robot target tracking, involve the execution of information acquisition tasks by teams of mobile robots. However, in failure-prone or adversarial environments, robots get attacked, their communication channels get jammed, and their sensors may fail…
We present a method for fast training of vision based control policies on real robots. The key idea behind our method is to perform multi-task Reinforcement Learning with auxiliary tasks that differ not only in the reward to be optimized but also in the state-space in which they operate. In particular, we allow auxilia…
Bayesian optimization adapts domain parameters for more robust robot policies.
While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where aspects of the environment needed to compute progress are not directly accessibl…
Robots hold promise in many scenarios involving outdoor use, such as search-and-rescue, wildlife management, and collecting data to improve environment, climate, and weather forecasting. However, autonomous navigation of outdoor trails remains a challenging problem. Recent work has sought to address this issue using de…
The automatic and efficient discovery of skills, without supervision, for long-living autonomous agents, remains a challenge of Artificial Intelligence. Intrinsically Motivated Goal Exploration Processes give learning agents a human-inspired mechanism to sequentially select goals to achieve. This approach gives a new p…
Proposes KStar Diffuser for kinematics-aware bimanual robotic manipulation.
A decentralized deep RL controller improves hexapod locomotion learning.
TIDBD adapts step sizes online for better robotic predictions.
Robot-assisted dressing offers an opportunity to benefit the lives of many people with disabilities, such as some older adults. However, robots currently lack common sense about the physical implications of their actions on people. The physical implications of dressing are complicated by non-rigid garments, which can r…
A new model for simulating cloth manipulation in robots, accurate to within 1cm.
Model-free deep reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. However, these methods typically suffer from two major challenges: high sample complexity and brittleness to hyperparameters. Both of these challenges limit the a…
Paper presents a method for efficient robot adaptation using fine-tuning.
Enhances neural rendering with geometry-aware attention.
Paper proposes a method to improve off-policy reinforcement learning in batch settings.
Depth perception is a key component for autonomous systems that interact in the real world, such as delivery robots, warehouse robots, and self-driving cars. Tasks in autonomous robotics such as 3D object recognition, simultaneous localization and mapping (SLAM), path planning and navigation, require some form of 3D sp…
This work analyzes how multi-agent reinforcement learning can bridge the gap to reality in distributed multi-robot systems.
Paper introduces timing-based adversarial attacks on DRL-based navigation systems.
ROBOT framework solves regression without correspondence for large data and complex models.
Deep RL trains a robust humanoid push-recovery policy.