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…
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.
168,878 papers · 148 categories
Trend · papers per month
48 results for “skill acquisition”
HiPPO adapts skills and higher-level policies together for better transfer in hierarchical RL.
problem Sub-optimality in skill transfer when lower-level skills are fixed.
method HiPPO: a novel hierarchical policy gradient method that trains all levels of the hierarchy jointly.
result Improved robustness of skills to environment changes through training time-abstractions.
New algorithm trains neural nets on simple skills to learn complex tasks faster.
problem Learning complex tasks through simple imitation.
method Train neural networks on simple, easy-to-learn skills to accelerate learning of complex, hard-to-learn tasks.
result Consistently outperforms state-of-the-art baseline in training speed and performance.
Autonomous Goal Exploration using Learned Goal Spaces for Visuomotor Skill Acquisition in Robotscs.LG
Robotic arm learns to manipulate a ball by choosing goals from learned experience.
problem Efficient discovery of skills for long-living autonomous agents without supervision.
method Intrinsically motivated goal exploration using learned goal spaces from deep representation learning.
result Recent results show applicability of learned goal spaces on real-world robotic tasks.
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.
Paper tackles skill transfer in RL for morphologically different agents.
problem Transfer skills between morphologically different reinforcement learning agents.
method Proposes a paired variational encoder-decoder model (PVED) for subspace learning.
result Demonstrates improved skill transfer efficiency compared to state-of-the-art methods.
Framework for lifelong learning using eigentasks to avoid forgetting and transfer knowledge.
problem Avoiding forgetting and transferring knowledge in lifelong learning.
method Eigentask framework: skills paired with generative models, wake-sleep cycle for learning and consolidation.
result Improved performance in supervised continual learning, evidence of forward knowledge transfer.
NetHack Learning Environment (NLE) tests RL algorithms, offering scalable, complex, and challenging gameplay.
problem Challenging environments for testing RL algorithms.
method Procedurally generated, stochastic, rich, and complex NetHack environment.
result Demonstrates empirical success for early stages of NetHack using RL.
qDKT improves KT models by considering individual question outcomes.
problem Ignoring question-specific outcomes leads to inaccurate learner skill tracking.
method qDKT incorporates graph Laplacian regularization and uses a fastText-inspired initialization scheme.
result qDKT achieves state-of-the-art performance in predicting learner outcomes.
This paper introduces our solution to the 2018 Duolingo Shared Task on Second Language Acquisition Modeling (SLAM). We used deep factorization machines, a wide and deep learning model of pairwise relationships between users, items, skills, and other entities considered. Our solution (AUC 0.815) hopefully managed to bea…
Option Encoder compresses reinforcement learning options into a policy basis.
problem Redundant options in reinforcement learning frameworks.
method Auto-encoder framework with constrained weights to discover a policy basis.
result Option Encoder reduces the number of options while maintaining performance.
New approach decouples skill learning and language grounding for autonomous agents.
problem Autonomous acquisition of skills without external instructions and feedback.
method Language-Goal-Behavior (LGB) architecture with semantic representation.
result Decouples skill learning and language grounding, enabling diversity and strategy switching.
Mass algorithm predicts M&A deals from patent data.
problem Hard to automatically predict M&A deals due to complex human skills.
method Machine learning-based similarity measure (MASS) applied to patent data.
result MASS outperforms LightGCN in forecasting M&A deals.
Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that together contribute to the development and specialization of our sensorimotor sk…
ReSkill reconciles RL skill creation with policy optimization.
problem RL policies lack reusable strategies across tasks.
method Integrates skill creation into RL loop with three mechanisms.
result Consistently outperforms existing methods, especially on unseen tasks.
Hierarchical MARL learns complementary skills for team coordination.
problem Creating intelligent agents that coordinate like human sports teams.
method Two-level hierarchical MARL with unsupervised skill discovery.
result Emergence of useful and complementary skills in team games.
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…
Robotics learns new skills faster by reusing past movements.
problem Learning new motor skills is time-consuming and requires exploration of a large space of motor configurations.
method Combines probabilistic movement primitives with relative entropy policy search for skill initialization and adaptation.
result Quality of learned skills improves and the number of required iterations to learn a new task can be reduced by more than 60%.
Bayesian nonparametrics enables dynamic skill discovery from expert data.
problem Fixed K for offline skill discovery in reinforcement learning.
method Variational inference, continuous relaxations, Bayesian nonparametrics.
result Nonparametric model with dynamically-changing number of options.
Paper learns skill distributions from game outcomes, proving minimax optimality.
problem Learning skill distributions from noisy pairwise game outcomes.
method Proposes a simple algorithm using kernel density estimation and minimax techniques.
result Near-optimal minimax mean squared error scaling for skill density estimation.
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…
The paper explains how language models acquire complex skills through scaling laws and statistical analysis.
problem Understanding how language models acquire new skills as their size and training data increase.
method Statistical framework and mathematical analysis of scaling laws.
result Language models can learn complex skills efficiently due to a strong inductive bias.
Convolutional neural networks improve surgical skill evaluation.
problem Manual feedback from senior surgeons is laborious, expensive, and subjective.
method Fully convolutional neural networks (CNNs) for classifying and regressing surgical skills.
result Deep neural networks achieve competitive performance on JIGSAWS dataset.
Researchers study how skills are learned in neural networks using physics principles.
problem Understanding how skills are sequentially learned in neural networks.
method Abstract and simplify the problem using physics principles, proposing three models: Geometry, Resource, and Domino.
result Models reveal insights into neural scaling laws, learning dynamics, and the benefits of modularity.
Misspecifying non-compensatory as compensatory IRT: analysis of estimated skills and variancestat.ME
The paper examines skill estimation and variance under model misspecification in IRT.
problem Underestimation and overestimation of skills when non-compensatory model is misspecified as compensatory.
method Theoretical approach to analyze underestimation and overestimation of skills and variance.
result Overestimation of skills occurs around the origin and asymptotic variance differs under model misspecification.
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…
ABC method improves subseasonal weather forecasting by 60-90%.
problem Improving subseasonal temperature and precipitation forecasting accuracy.
method Combines dynamical forecasts with machine learning-based bias correction.
result Significant improvement in temperature and precipitation forecasting skills.
DSE learns transferable skills across changing dynamics and goals.
problem Learning transferable skills across different reinforcement learning tasks.
method Variational inference for multi-task reinforcement learning with shared and task-specific latent spaces.
result Policies can generalize to unseen dynamics and goals conditions.
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…
A planning approach learns skills from interactions, balancing exploration and exploitation.
problem Learning robust high-level skills in noisy environments with unknown pre-conditions.
method Formulates skills as high-level policies, learns plans via bandit problems, balances exploration and exploitation.
result A planner capable of learning robust high-level skills in high-dimensional state spaces.
DADS discovers skills with predictable outcomes from unlabeled data.
problem Learning accurate models for complex dynamical systems is difficult and often doesn't generalize well.
method Dynamics-Aware Discovery of Skills (DADS) combines model-based and model-free learning.
result DADS discovers infinitely many behaviors in high-dimensional state-spaces.
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 …
Integrates skills and world models for efficient task solving and transfer.
problem Quickly solve new tasks in complex environments using reusable knowledge.
method Leverages partial amortization for fast adaptation and online skill planning.
result Improved sample efficiency in single tasks and transfer between tasks.
EDL discovers state-covering skills without relying on task rewards.
problem Discovering skills in reinforcement learning without a task-oriented reward function.
method EDL optimizes information-theoretic objective using different machinery to address coverage problem.
result EDL discovers state-covering skills more effectively than existing methods.
Sloth predicts LLM performance using latent skills across families.
problem Variations in benchmark performance due to differences in training configurations and data processing across model families.
method Sloth uses publicly available benchmark data and assumes LLM performance is driven by latent skills influenced by model size and training tokens. It exploits correlations across benchmarks to provide accurate predictions.
result Sloth predicts LLM performance accurately and offers insights into scaling behaviors for complex tasks.
The paper presents a method for personalized exercise recommendations that improves learner skill gain.
problem Adapting to individual needs in large, diverse groups of learners in digital environments.
method Contextual Thompson Sampling to select exercises that advance learner skill.
result The method recommends exercises associated with greater skill improvement and adapts to learner differences.
New methods for skill rating in sports using state-space models.
problem Improving skill rating in competitive sports.
method State-space models, sequential Monte Carlo, discrete hidden Markov models.
result Advantages of state-space models for time-varying player skills.
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…
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…
Meta-World benchmark tests meta-reinforcement learning on 50 robotic tasks.
problem Current meta-reinforcement learning benchmarks are too narrow, limiting generalization.
method Proposes a new benchmark with 50 robotic manipulation tasks.
result State-of-the-art algorithms struggle with multiple tasks simultaneously.
A new method learns policies from sub-optimal trajectories.
problem Reinforcement learning's brittleness and difficulty in tuning.
method Conditioning policies on the reward of sub-optimal trajectories.
result Effective policies can be learned without expert demonstrations.
New method boosts skill learning by encouraging optimistic exploration.
problem Intrinsic reward for exploration is inherently pessimistic.
method Derive an information gain auxiliary objective involving an ensemble of discriminators and rewarding policy disagreement.
result Improves skill learning in grid worlds and Atari games.
We consider worker skill estimation for the single-coin Dawid-Skene crowdsourcing model. In practice, skill-estimation is challenging because worker assignments are sparse and irregular due to the arbitrary and uncontrolled availability of workers. We formulate skill estimation as a rank-one correlation-matrix completi…
Paper learns versatile balancing and recovery motions for humanoid robots.
problem Training humanoid robots to handle unexpected perturbations.
method Hierarchical Deep Reinforcement Learning in a physics simulator.
result Learned skills comparable to preprogrammed controllers but more adaptable.
Multiplayer Online Battle Arena (MOBA) games are among the most played digital games in the world. In these games, teams of players fight against each other in arena environments, and the gameplay is focused on tactical combat. Mastering MOBAs requires extensive practice, as is exemplified in the popular MOBA Defence o…
New method automates asymmetric choice for better skill transfer in reinforcement learning.
problem Improving sample efficiency and transferability of reinforcement learning agents.
method Attentive Priors for Expressive and Transferable Skills (APES) using hierarchical KL-regularization.
result APES automates asymmetric choice, leading to better skill transfer across sequential tasks.
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 …