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.
ReSkill reconciles RL skill creation with policy optimization.
Human players in professional team sports achieve high level coordination by dynamically choosing complementary skills and executing primitive actions to perform these skills. As a step toward creating intelligent agents with this capability for fully cooperative multi-agent settings, we propose a two-level hierarchica…
Bayesian nonparametrics enables dynamic skill discovery from expert data.
We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation-reality gap, we learn a set of diverse policies that are parameterized in a way that makes them easily reusable. This diversity and p…
We introduce the Adaptive Skills, Adaptive Partitions (ASAP) framework that (1) learns skills (i.e., temporally extended actions or options) as well as (2) where to apply them. We believe that both (1) and (2) are necessary for a truly general skill learning framework, which is a key building block needed to scale up t…
Researchers study how skills are learned in neural networks using physics principles.
Paper learns skill distributions from game outcomes, proving minimax optimality.
Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment. An open problem in this setting is that of developing good strategies for integrating or merging policies for multiple skills, where each…
Acquiring new robot motor skills is cumbersome, as learning a skill from scratch and without prior knowledge requires the exploration of a large space of motor configurations. Accordingly, for learning a new task, time could be saved by restricting the parameter search space by initializing it with the solution of a si…
Employers actively look for talents having not only specific hard skills but also various soft skills. To analyze the soft skill demands on the job market, it is important to be able to detect soft skill phrases from job advertisements automatically. However, a naive matching of soft skill phrases can lead to false pos…
New algorithm trains neural nets on simple skills to learn complex tasks faster.
A planning approach learns skills from interactions, balancing exploration and exploitation.
Simulation-to-real transfer is an important strategy for making reinforcement learning practical with real robots. Successful sim-to-real transfer systems have difficulty producing policies which generalize across tasks, despite training for thousands of hours equivalent real robot time. To address this shortcoming, we…
Integrates skills and world models for efficient task solving and transfer.
Spaced repetition is among the most studied learning strategies in the cognitive science literature. It consists in temporally distributing exposure to an information so as to improve long-term memorization. Providing students with an adaptive and personalized distributed practice schedule would benefit more than just …
Humans are able to perform a myriad of sophisticated tasks by drawing upon skills acquired through prior experience. For autonomous agents to have this capability, they must be able to extract reusable skills from past experience that can be recombined in new ways for subsequent tasks. Furthermore, when controlling com…
For robots to coexist with humans in a social world like ours, it is crucial that they possess human-like social interaction skills. Programming a robot to possess such skills is a challenging task. In this paper, we propose a Multimodal Deep Q-Network (MDQN) to enable a robot to learn human-like interaction skills thr…
We introduce a method for constructing skills capable of solving tasks drawn from a distribution of parameterized reinforcement learning problems. The method draws example tasks from a distribution of interest and uses the corresponding learned policies to estimate the topology of the lower-dimensional piecewise-smooth…
ABC method improves subseasonal weather forecasting by 60-90%.
Conventionally, model-based reinforcement learning (MBRL) aims to learn a global model for the dynamics of the environment. A good model can potentially enable planning algorithms to generate a large variety of behaviors and solve diverse tasks. However, learning an accurate model for complex dynamical systems is diffi…
New method boosts skill learning by encouraging optimistic exploration.
The paper explains how language models acquire complex skills through scaling laws and statistical analysis.
E-learning systems are capable of providing more adaptive and efficient learning experiences for students than the traditional classroom setting. A key component of such systems is the learning strategy, the algorithm that designs the learning paths for students based on information such as the students' current progre…
The composition of elementary behaviors to solve challenging transfer learning problems is one of the key elements in building intelligent machines. To date, there has been plenty of work on learning task-specific policies or skills but almost no focus on composing necessary, task-agnostic skills to find a solution to …
New method automates asymmetric choice for better skill transfer in reinforcement learning.
Purpose: Manual feedback from senior surgeons observing less experienced trainees is a laborious task that is very expensive, time-consuming and prone to subjectivity. With the number of surgical procedures increasing annually, there is an unprecedented need to provide an accurate, objective and automatic evaluation of…
The paper presents a method for personalized exercise recommendations that improves learner skill gain.
Acquiring abilities in the absence of a task-oriented reward function is at the frontier of reinforcement learning research. This problem has been studied through the lens of empowerment, which draws a connection between option discovery and information theory. Information-theoretic skill discovery methods have garnere…
Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a higher level that controls the skills in a new task. Leaving the skills fixed can le…
New method learns robot skills from data, matching or outperforming existing methods.
This paper presents a hierarchical framework for Deep Reinforcement Learning that acquires motor skills for a variety of push recovery and balancing behaviors, i.e., ankle, hip, foot tilting, and stepping strategies. The policy is trained in a physics simulator with realistic setting of robot model and low-level impeda…
Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a nov…
We propose a novel framework for multi-task reinforcement learning (MTRL). Using a variational inference formulation, we learn policies that generalize across both changing dynamics and goals. The resulting policies are parametrized by shared parameters that allow for transfer between different dynamics and goal condit…
Robots can rapidly acquire new skills from demonstrations. However, during generalisation of skills or transitioning across fundamentally different skills, it is unclear whether the robot has the necessary knowledge to perform the task. Failing to detect missing information often leads to abrupt movements or to collisi…
Transformers learn to solve modular arithmetic tasks by in-context learning and skill composition.
Transfer learning methods for reinforcement learning (RL) domains facilitate the acquisition of new skills using previously acquired knowledge. The vast majority of existing approaches assume that the agents have the same design, e.g. same shape and action spaces. In this paper we address the problem of transferring pr…
Paper tackles multi-object reinforcement learning, improving skill extrapolation.
SUPE combines unlabeled data with RL to efficiently explore tasks.
Solves a model for sudden problem-solving ability in deep learning.
Evaluating surgeon skill has predominantly been a subjective task. Development of objective methods for surgical skill assessment are of increased interest. Recently, with technological advances such as robotic-assisted minimally invasive surgery (RMIS), new opportunities for objective and automated assessment framewor…
Framework for lifelong learning using eigentasks to avoid forgetting and transfer knowledge.
The paper examines skill estimation and variance under model misspecification in IRT.
An important property for lifelong-learning agents is the ability to combine existing skills to solve unseen tasks. In general, however, it is unclear how to compose skills in a principled way. We provide a "recipe" for optimal value function composition in entropy-regularised reinforcement learning (RL) and then exten…
Deep reinforcement learning (DRL) is capable of learning high-performing policies on a variety of complex high-dimensional tasks, ranging from video games to robotic manipulation. However, standard DRL methods often suffer from poor sample efficiency, partially because they aim to be entirely problem-agnostic. In this …
AMIGo uses adversarial intrinsic goals to teach RL agents new skills.
Background: Virtual reality simulators and machine learning have the potential to augment understanding, assessment and training of psychomotor performance in neurosurgery residents. Objective: This study outlines the first application of machine learning to distinguish "skilled" and "novice" psychomotor performance du…
Triple-GAIL learns from multiple sources to improve imitation learning for complex behaviors.
Sloth predicts LLM performance using latent skills across families.