When machine predictors can achieve higher performance than the human decision-makers they support, improving the performance of human decision-makers is often conflated with improving machine accuracy. Here we propose a framework to directly support human decision-making, in which the role of machines is to reframe pr…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Human Learning”
Reward shaping speeds up human learning through IRL.
problem Slow learning in humans, especially for challenging tasks.
method Extended IRL algorithm with kernel methods, conducted experiments with online game players.
result Players learn desired policies more quickly with reward shaping.
This paper argues for more realistic human models in RL.
problem Current RL models oversimplify human feedback, ignoring personal, contextual, and dynamic aspects.
method Calls for interdisciplinary research on human feedback in RL.
result Realistic human models are needed for robust human-in-the-loop RL systems.
IDT learns human preferences from uncertain decisions, even when humans are suboptimal.
problem Learning human preferences from uncertain and suboptimal decisions.
method Inverse decision theory (IDT) framework, statistical analysis of IDT, characterizing sample complexity.
result Learning preferences is easier when decisions are more uncertain, even if humans are suboptimal.
This research integrates human interaction into reinforcement learning to improve sample efficiency and real-time learning.
problem Current reinforcement learning requires thousands of samples to converge, and is prone to catastrophic failures.
method Integrates human interaction modalities (demonstrations, interventions, evaluations) into the reinforcement learning loop.
result Human interaction accelerates learning and improves sample efficiency.
This work compares human feedback methods for reward learning in bandits.
problem Understanding how human feedback affects the performance of reward learning methods.
method Theoretical comparison of human feedback approaches in offline contextual bandits.
result Human bias and uncertainty in feedback modeling impact the theoretical guarantees of reward learning methods.
Humans are the final decision makers in critical tasks that involve ethical and legal concerns, ranging from recidivism prediction, to medical diagnosis, to fighting against fake news. Although machine learning models can sometimes achieve impressive performance in these tasks, these tasks are not amenable to full auto…
Let Me At Least Learn What You Really Like: Dealing With Noisy Humans When Learning Preferencescs.LG
Paper proposes a modified uncertainty sampling method to speed up preference learning from noisy humans.
problem Learning preferences from humans with limited queries and noisy responses.
method Modified uncertainty sampling using expected output value to speed up preference learning.
result The modified method outperforms the baseline uncertainty sampling in preference learning.
To coordinate actions with an interaction partner requires a constant exchange of sensorimotor signals. Humans acquire these skills in infancy and early childhood mostly by imitation learning and active engagement with a skilled partner. They require the ability to predict and adapt to one's partner during an interacti…
Enhances AI models with human feedback for noisy data.
problem Improving AI model alignment with human feedback in noisy environments.
method Two-stage SL+LHF framework connecting machine learning with human feedback.
result The LNCA ratio identifies conditions for SL+LHF superiority over pure SL.
The Human Kernelcs.LG
Bayesian nonparametric models, such as Gaussian processes, provide a compelling framework for automatic statistical modelling: these models have a high degree of flexibility, and automatically calibrated complexity. However, automating human expertise remains elusive; for example, Gaussian processes with standard kerne…
This thesis tackles learning reward functions from human comparative feedback.
problem Designing reward functions for complex tasks is challenging and humans often provide suboptimal demonstrations.
method Proposes learning reward functions from comparative feedback (pairwise comparisons, best-of-many choices, rankings, scaled comparisons) and active learning techniques.
result Demonstrates the effectiveness of learning reward functions from comparative feedback in various domains.
Conformal prediction sets improve human decision making by quantifying model uncertainty.
problem Humans signal uncertainty and offer alternatives when unsure, but machine learning models often lack this feature.
method Conducted a randomized controlled trial with human subjects given conformal prediction sets.
result Human accuracy improves when given conformal prediction sets compared to fixed-size prediction sets.
Human irrationality can improve AI design, study shows.
problem Improving AI by learning from human decision-making biases.
method Developed a novel POMDP model to simulate human decision-making in contextual choice tasks.
result Reinforcement learners can exploit human irrationalities to make better decisions.
While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to them can converge to coordination protocols that fail to understand and be unders…
Paper tackles RLHF with DCPPO method, proving near-optimal suboptimality.
problem Challenges in offline RLHF with limited human feedback and bounded rationality.
method DCPPO method involving three stages: MLE, reward function recovery, and pessimistic value iteration.
result DCPPO's suboptimality almost matches classical pessimistic offline RL in terms of distribution shift and dimension.
PILAF optimizes reward models from human feedback for better policy alignment.
problem Creating accurate reward models from human feedback for policy optimization.
method Policy-Interpolated Learning for Aligned Feedback (PILAF) that explicitly aligns preference learning with maximizing underlying oracle reward.
result PILAF is optimal from both optimization and statistical perspectives, demonstrating strong performance in RLHF settings.
Dual active learning improves RLHF by selecting optimal conversations and teachers.
problem Efficiently aligning LLMs with human preferences using RLHF from feedback.
method Offline RL for conversation and teacher selection, dual active reward learning, pessimistic RL.
result The proposed algorithm achieves minimal generalized variance and outperforms state-of-the-arts.
A new approach to fine-tuning LLMs with human feedback.
problem Inability of current reward models to fully represent human preferences.
method Introducing NLHF, a new pipeline for LLM fine-tuning using pairwise human feedback.
result NLHF produces a sequence of policies converging to the regularized Nash equilibrium.
Counterfactual learning from human bandit feedback describes a scenario where user feedback on the quality of outputs of a historic system is logged and used to improve a target system. We show how to apply this learning framework to neural semantic parsing. From a machine learning perspective, the key challenge lies i…
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…
Learning preferences implicit in the choices humans make is a well studied problem in both economics and computer science. However, most work makes the assumption that humans are acting (noisily) optimally with respect to their preferences. Such approaches can fail when people are themselves learning about what they wa…
AlphaZero reveals new chess concepts learnable by top experts.
problem Extracting and understanding hidden knowledge from AI systems.
method Proposed method to extract new chess concepts from AlphaZero.
result Top chess grandmasters show improvements in learning new concepts.
Study models human investors' sub-rational behavior in financial markets.
problem Lack of a comprehensive model for human sub-rationality in financial markets.
method Flexible reinforcement learning model incorporating five human sub-rational aspects.
result Model accurately reproduces human behavior and reveals insights into market dynamics.
Autonomous agents trained via reinforcement learning present numerous safety concerns: reward hacking, negative side effects, and unsafe exploration, among others. In the context of near-future autonomous agents, operating in environments where humans understand the existing dangers, human involvement in the learning p…
Large-scale public datasets have been shown to benefit research in multiple areas of modern artificial intelligence. For decision-making research that requires human data, high-quality datasets serve as important benchmarks to facilitate the development of new methods by providing a common reproducible standard. Many h…
RLHF fails when humans only partially observe, leading to inflated or overjustified feedback.
problem Failure of reinforcement learning from human feedback in partially observable environments.
method Formal definition of failure cases, modeling human as Boltzmann rational, analyzing information provided by feedback.
result RLHF can deceptively inflate or overjustify feedback when humans have partial observations.
A test measures artificial agents' human-like behavior in video games.
problem Measuring the believability of artificial agents' human-like behavior.
method Developed a non-parametric two-sample hypothesis test.
result The -value correlates with human judgment of human-like behavior.
The paper tackles AI advice giving by considering adherence levels and defer options.
problem Inadequate consideration of human adherence to AI recommendations.
method Sequential decision-making model that considers adherence levels and incorporates a defer option.
result Specialized learning algorithms provide better convergence and empirical performance.
Active IRL selects optimal human demonstrations for learning AI preferences.
problem Costly human demonstrations in IRL for autonomous systems.
method Information-theoretic acquisition function for selecting informative human demonstrations.
result Efficiently reduces human effort in learning AI preferences.
Deep RL mimics human driving for collision avoidance in self-driving cars.
problem Developing human-like driving policies for autonomous vehicles in mixed traffic environments.
method Model-free, deep reinforcement learning approach using a combination of rule-based and expert-driven data.
result Demonstrated human-like driving policies through Gaussian process modeling of track position and speed distributions.
Programmatic Motion Concepts learn human actions from paired videos.
problem Learning motion concepts from paired video and action sequences.
method Semi-supervised learning architecture for hierarchical motion representation.
result Outperforms established baselines, especially in small data settings.
Generative classifiers show surprising human-like performance.
problem Comparing generative and discriminative models for object recognition.
method Built on recent advances in generative modeling to create classifiers and compared them to discriminative models.
result Generative classifiers outperform discriminative models in several key areas, including shape bias and out-of-distribution accuracy.
Study evaluates new models using human feedback from another model.
problem Evaluate a new model using human feedback collected for another model.
method Formalize problem, propose model-based and model-free estimators, analyze unbiasedness, and empirically evaluate.
result Proposed estimators can predict absolute values, rank, and optimize evaluated policies.
We present a novel human-aware navigation approach, where the robot learns to mimic humans to navigate safely in crowds. The presented model, referred to as DeepMoTIon, is trained with pedestrian surveillance data to predict human velocity in the environment. The robot processes LiDAR scans via the trained network to n…
Unified LP framework for offline reward learning from human demonstrations and feedback.
problem Reward learning from human demonstrations and feedback with robustness and sample efficiency.
method A novel linear programming framework for offline reward learning.
result Unified LP framework achieves better performance compared to MLE.
Have you ever looked at a machine learning classification model and thought, I could have made that? Well, that is what we test in this project, comparing XGBoost trained on human engineered features to training directly on data. The human engineered features do not outperform XGBoost trained di- rectly on the data, bu…
Algorithm learns actions from past states in complex tasks.
problem Learning policies from human feedback is expensive.
method Combining learned feature encoder with inverse models to simulate past actions.
result Algorithm can infer specific skills from single state.
Develops methods for cooperative Bayesian inference.
problem Cooperation between learning agents.
method Sequential Bayesian inference approaches.
result Theoretical foundation for cooperative inference.
Representation of human actions as a sequence of human body movements or action attributes enables the development of models for human activity recognition and summarization. We present an extension of the low-rank representation (LRR) model, termed the clustering-aware structure-constrained low-rank representation (CS…
AI models aligned with human vision perform well on few data tasks.
problem Few-shot learning performance with limited data.
method Information-theoretic analysis and empirical testing of 491 models.
result Highly aligned models show better robustness to attacks and domain shifts.
To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users. Moreover, they will need to learn these behaviors within a reasonable amount of time while efficiently leveraging the sparse feedback a human trainer is capable o…
Paper explores limits and possibilities of aligning LLMs with human preferences.
problem Aligning LLMs with diverse human preferences to ensure fairness and informed outcomes.
method Analysis of probabilistic representation of human preferences and preservation of diverse preferences.
result LLMs can't fully align with human preferences using reward-based approaches due to Condorcet cycles, but mixed strategies are statistically possible.
The abstract discusses how humans use visualizations in machine learning.
problem The reliance on human involvement in AI systems and analytics.
method Review of seven steps in the ML process and different visualization techniques.
result Different visualizations are used at various stages of the ML process.
What makes a task relatively more or less difficult for a machine compared to a human? Much AI/ML research has focused on expanding the range of tasks that machines can do, with a focus on whether machines can beat humans. Allowing for differences in scale, we can seek interesting (anomalous) pairs of tasks T, T'. We d…
Paper proposes a new RLHF framework for human preference learning.
problem Handling dependent online human preference outcomes with dynamic contexts.
method Two-stage algorithm with -greedy followed by exploitation; anti-concentration inequalities and matrix martingale concentration techniques.
result Our method achieves optimal regret bound and asymptotic normality of estimators.
Human decision-making underlies all economic behavior. For the past four decades, human decision-making under uncertainty has continued to be explained by theoretical models based on prospect theory, a framework that was awarded the Nobel Prize in Economic Sciences. However, theoretical models of this kind have develop…
The paper tackles learning from imperfect human feedback, especially in dueling bandit problems.
problem Learning from human feedback that can be irrational or imperfect.
method Developed a Robustified Stochastic Mirror Descent for Imperfect Dueling (RoSMID) algorithm.
result Achieved nearly optimal regret for dueling bandit problems under imperfect human feedback.