The current dominant paradigm for imitation learning relies on strong supervision of expert actions to learn both 'what' and 'how' to imitate. We pursue an alternative paradigm wherein an agent first explores the world without any expert supervision and then distills its experience into a goal-conditioned skill policy …
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Zero-Shot Imitation”
Unified framework for imitating tasks across domains with discrepancies.
problem Learning tasks across domains with embodiment, viewpoint, and dynamics mismatches.
method Two-step approach: alignment followed by adaptation. Alignment uses Generative Adversarial MDP Alignment (GAMA) for state and action correspondences from unpaired, unaligned demonstrations. Adaptation leverages these correspondences for zero-shot imitation.
result Effectiveness of the proposed approach in embodiment, viewpoint, and dynamics mismatch scenarios.
New method improves RL/IL agents' adaptability to unseen environments.
problem Current RL/IL techniques struggle with generalizing to unseen environments.
method Zero-shot compositional policy learning with multi-modal fusion and attention mechanism.
result Language grounding enhances generalization across varied environments.
Hierarchical decoupling improves sample efficiency for complex robots.
problem Learning long-range behaviors on complex robots.
method Two-part policy: low-level imitation and high-level transfer, with KL regularization.
result Hierarchical transfer significantly improves zero-shot high-level transfer and stabilizes learning.
New method aligns states for better imitation learning.
problem Different dynamics models between imitator and expert.
method State alignment-based reinforcement learning.
result Superior performance on various imitation learning settings.
Zero-shot anomaly detection method using batch normalization.
problem Adapting anomaly detectors to new normal data distributions without training data.
method Adaptive Centered Representations (ACR) with batch normalization.
result First zero-shot AD results for tabular data and image data.
Paper proposes redundancy-free features for zero-shot object recognition.
problem Redundant visual features degrade zero-shot object recognition.
method Project original features into a new, statistically independent space.
result RFF-GZSL achieves competitive results on benchmark datasets.
ADVISOR dynamically balances imitation and reinforcement learning to overcome the imitation gap.
problem The gap between imitation learning and reinforcement learning when teaching agents have privileged information.
method Adaptive Insubordination (ADVISOR) dynamically weights imitation and reward-based reinforcement learning losses.
result On-the-fly switching with ADVISOR outperforms pure imitation, pure reinforcement learning, and their combinations.
Zero-shot learning transfers knowledge from seen classes to novel unseen classes to reduce human labor of labelling data for building new classifiers. Much effort on zero-shot learning however has focused on the standard multi-class setting, the more challenging multi-label zero-shot problem has received limited attent…
Paper explores zero-shot cross-lingual reading comprehension using pre-trained multi-lingual model.
problem Lack of training data for every language in reading comprehension tasks.
method Systematic exploration of zero-shot cross-lingual transfer learning with a multi-lingual language representation model.
result Zero-shot cross-lingual transfer learning is feasible and translating source data into target language is not necessary.
Study shows zero-shot super-resolution in neural operators is impossible in many cases.
problem Understanding the theoretical limits of zero-shot super-resolution in neural operators.
method Systematic theoretical study including information-theoretic and generalization bounds analysis.
result Zero-shot super-resolution is information-theoretically impossible in many settings.
Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, which poses a significant challenge in some scenarios. A promising altern…
Aggregates diverse zero-shot LLM outputs for better corporate disclosure classification.
problem Combining varied zero-shot LLM predictions for improved stock return prediction.
method Multi-prompt framework with three fixed zero-shot LLM classifiers, logistic meta-classifier aggregation.
result Aggregated model outperforms single classifiers and baseline models, increasing balanced accuracy from 0.566 to 0.606.
Reinforcement learning mimics expert behavior.
problem Learning from expert demonstrations in reinforcement learning.
method Reduction to reinforcement learning with a stationary reward.
result Expert reward can be recovered and imitation learning is bounded.
Guarantees for third-person imitation learning from offline data.
problem Improving generalizability in imitation learning.
method Problem-dependent statistical learning guarantees for third-person imitation from offline observation.
result Strong performance guarantees for transferred policies in the offline setting.
Generalization and reliability of multilingual translation often highly depend on the amount of available parallel data for each language pair of interest. In this paper, we focus on zero-shot generalization---a challenging setup that tests models on translation directions they have not been optimized for at training t…
TRAIL improves robot imitation learning by focusing on task-relevant features.
problem Discriminator networks learn spurious associations, providing poor reward signals.
method Constrained discriminator optimization to learn task-relevant rewards.
result TRAIL outperforms GAIL and behaviour cloning in robotic manipulation tasks.
Paper improves zero-shot protein stability prediction by clarifying free-energy foundations.
problem Improving zero-shot protein stability prediction using inverse folding models.
method Clarifying the free-energy foundations of inverse folding models and proposing better estimates of relative stability.
result Significant gains in zero-shot performance can be achieved with simple methods.
GWIL uses Gromov-Wasserstein distance to align expert and imitation agent states.
problem Cross-domain imitation learning challenges due to different system dimensions and stationary distributions.
method Gromov-Wasserstein Imitation Learning (GWIL) using Gromov-Wasserstein distance.
result GWIL effectively aligns expert and imitation agent states in various continuous control domains.
This study evaluates zero-shot LLMs in finance, finding ChatGPT performs well but fine-tuned models are better.
problem Evaluating zero-shot LLMs in financial tasks.
method Comparison of ChatGPT and fine-tuned models on annotated data.
result Fine-tuned models generally outperform zero-shot LLMs.
Study uses zero-shot models to forecast mortality rates globally.
problem Forecasting mortality rates without task-specific fine-tuning.
method Two state-of-the-art foundation models (TimesFM and CHRONOS) and traditional/machine learning methods were evaluated.
result CHRONOS outperformed traditional methods for shorter-term forecasts, but TimesFM consistently underperformed.
New metric solves correspondence problem for robotic arm imitation learning.
problem Establishing corresponding states and actions between different robotic arms.
method Introducing a distance measure between dissimilar robotic arms and using it as a loss function.
result The distance measure effectively learns imitation policies by minimizing distance between robotic arms.
Paper tackles zero-shot activity recognition using video features and text embeddings.
problem Zero-shot activity recognition with videos.
method Auto-encoder model for multimodal joint embedding, 3D convolutional action recognition for visual features, GloVe word embeddings for textual features.
result Improved zero-shot recognition results with top-n accuracy and mean Nearest Neighbor Overlap.
Study optimal investment under imitation of decision-changing rates.
problem Optimal investment under imitation of decision-changing rates.
method Proposed integral disparity to quantify imitation, derived general solution using variational method, analyzed asymptotic properties, validated with real data.
result Investor's optimal decisions under imitation of decision-changing rates.
We address the problem of learning fine-grained cross-modal representations. We propose an instance-based deep metric learning approach in joint visual and textual space. The key novelty of this paper is that it shows that using per-image semantic supervision leads to substantial improvement in zero-shot performance ov…
A proof of imitation of Wasserstein inverse reinforcement learning for multi-objective optimizationcs.LG
Proof shows imitation of expert's reward and solutions in multi-objective optimization.
problem Multi-objective optimization with reward and solution imitation.
method Wasserstein inverse reinforcement learning.
result Wasserstein inverse reinforcement learning enables imitation of expert's reward and solutions in multi-objective optimization.
Researchers improved Minecraft game performance using imitation learning.
problem Achieving state-of-the-art performance in immersive environments like Minecraft.
method Applied imitation learning to Minecraft, optimizing network architecture, loss function, and data augmentation.
result Reported stronger results than previous experiments, reaching second place in a competition.
Paper tackles robust imitation learning from noisy demonstrations.
problem Learning from noisy demonstrations is challenging.
method Optimizes a classification risk with a symmetric loss, combining pseudo-labeling and co-training.
result Our method is more robust than state-of-the-art methods.
ZegOT uses optimal transport to zero-shot segment images with text prompts.
problem Zero-shot semantic segmentation with limited image-text alignment knowledge.
method ZegOT uses optimal transport to match multiple text prompts with frozen image embeddings.
result ZegOT achieves state-of-the-art performance in zero-shot semantic segmentation.
Paper uses Sinkhorn distances to improve imitation learning effectiveness.
problem Improving imitation learning algorithms by comparing occupancy measures.
method Formulates imitation learning as Sinkhorn distance minimization, combining optimal transport and cosine distances.
result Proposes a new critic network and transport plan that guide imitation learning.
Imitation from observation is the framework of learning tasks by observing demonstrated state-only trajectories. Recently, adversarial approaches have achieved significant performance improvements over other methods for imitating complex behaviors. However, these adversarial imitation algorithms often require many demo…
New method uses bi-level optimization to learn useful representations for imitation learning.
problem Learning useful representations for multiple tasks in imitation learning settings.
method Formulates representation learning as a bi-level optimization problem.
result Bi-level optimization framework provides sample complexity benefits for imitation learning.
Paper proposes CCVAE for generalized zero-shot domain adaptation.
problem Adapting to unseen classes in target domain with limited labeled data.
method Coupled Conditional Variational Autoencoder (CCVAE).
result CCVAE generates synthetic target domain features for unseen classes.
New self-imitation learning method improves performance in continuous control tasks.
problem Improving off-policy learning in continuous control tasks.
method Proposes a n-step lower bound to generalize lower-bound Q-learning and introduces a new family of self-imitation learning algorithms.
result n-step lower bound Q-learning achieves a better trade-off between bias and contraction rate, leading to improved performance.
NDI learns from expert demonstrations by estimating occupancy measures.
problem Imitation Learning (IL) for complex systems.
method Density estimation of expert's occupancy measure followed by RL.
result NDI achieves state-of-the-art performance on control tasks.
The paper analyzes the value discrepancies of imitation learning methods.
problem Analyzing the value discrepancies of imitation learning methods.
method Discrepancy propagation analysis for infinite-horizon settings.
result GAIL has less compounding errors than behavioral cloning.
Dissertation tackles zero-shot anomaly detection, focusing on consistent anomalies and proposing CoDeGraph framework.
problem Consistent anomalies bias distance-based zero-shot anomaly detection methods.
method Formalized consistent anomalies, identified similarity scaling and neighbor-burnout phenomena, introduced CoDeGraph framework.
result CoDeGraph effectively suppresses consistent anomalies in zero-shot anomaly detection.
New method improves imitation learning from expert observations.
problem Challenges in imitation learning from observation setting.
method Reparameterized Variational Divergence Minimization.
result Our method outperforms baseline approaches in low-dimensional tasks.
This work improves fairness in federated learning by using zero-shot data augmentation.
problem Statistical heterogeneity leads to biased and less uniform accuracy across clients in federated learning.
method Proposes a federated learning system with zero-shot data augmentation to mitigate statistical heterogeneity and improve fairness.
result Empirical results show improved test accuracy and fairness across clients.
Theory explains how AI models can predict unseen tasks without labeled data.
problem Understanding how AI models can generalize to unseen tasks.
method Developed a theoretical framework to analyze zero-shot prediction.
result Identified key quantities and independence relationships for generalization.
M2M tackles zero-shot structured noise suppression in images.
problem Structured noise with strong anisotropic correlations in real-world images.
method M2M introduces a novel sampling strategy that generates pseudo-independent sub-image pairs from a single noisy input, using directional interpolation and generalized median filtering.
result M2M consistently outperforms state-of-the-art zero-shot methods under correlated noise.
New method simplifies and improves imitation learning without adversarial techniques.
problem Stable optimization and convergence issues in adversarial imitation learning methods.
method Proposes a non-adversarial framework for imitation learning, providing stronger convergence guarantees.
result Shows AIRL as a special case and derives new algorithms for offline imitation learning.
CLIP learns joint image-text representations for zero-shot learning.
problem Understanding and improving zero-shot transfer performance in CLIP.
method Formal study of transferrable representation learning and analysis of zero-shot transfer performance.
result Proposes a new CLIP-type approach that outperforms existing methods.
We study risk-sensitive imitation learning where the agent's goal is to perform at least as well as the expert in terms of a risk profile. We first formulate our risk-sensitive imitation learning setting. We consider the generative adversarial approach to imitation learning (GAIL) and derive an optimization problem for…
Zero-shot understanding of accidents from surveillance videos using vision-language models
problem Accident understanding from surveillance videos
method Three-stage pipeline with vision-language similarity, metadata-driven multi-prompt reasoning, and entropy-gated pairwise adjudicator
result Substantial improvement in harmonic-mean score over baseline
A new algorithm trains experts to safely guide agents in partially observed environments.
problem Existing imitation learning methods for POMDPs can lead to sub-optimal or unsafe policies.
method Derive an objective to encourage the expert to maximize the agent's reward, then use it to train both expert and agent.
result The algorithm produces an expert policy that the agent can safely imitate, outperforming fixed expert policies.
Proposes a method to imitate active learning heuristics for better performance.
problem The performance of active learning heuristics depends on the classifier model and data structure.
method Imitates the selection of the best active learning heuristic using DAGGER.
result Outperforms state-of-the-art imitation learners and heuristics on well-known datasets.
Integration of reinforcement learning and imitation learning is an important problem that has been studied for a long time in the field of intelligent robotics. Reinforcement learning optimizes policies to maximize the cumulative reward, whereas imitation learning attempts to extract general knowledge about the traject…