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.
GWIL uses Gromov-Wasserstein distance to align expert and imitation agent states.
Dual-structured method improves cross-domain imitation learning.
Sparse coding has shown its power as an effective data representation method. However, up to now, all the sparse coding approaches are limited within the single domain learning problem. In this paper, we extend the sparse coding to cross domain learning problem, which tries to learn from a source domain to a target dom…
With the proliferation of social media platforms and e-commerce sites, several cross-domain collaborative filtering strategies have been recently introduced to transfer the knowledge of user preferences across domains. The main challenge of cross-domain recommendation is to weigh and learn users' different behaviors in…
ADGAN improves risk tolerance prediction by aligning cross-domain data.
Nowadays, users open multiple accounts on social media platforms and e-commerce sites, expressing their personal preferences on different domains. However, users' behaviors change across domains, depending on the content that users interact with, such as movies, music, clothing and retail products. In this paper, we pr…
CosML combines domain-specific meta-learners for cross-domain few-shot classification.
Consider an imitation learning problem that the imitator and the expert have different dynamics models. Most of the current imitation learning methods fail because they focus on imitating actions. We propose a novel state alignment-based imitation learning method to train the imitator to follow the state sequences in e…
This paper improves cross-domain learning using random forests for manifold alignment.
New approach improves cross-domain recommendation for sparse target domains.
Meta learning enables cross-domain Hamiltonian dynamics.
Cross-domain recommendation can alleviate the data sparsity problem in recommender systems. To transfer the knowledge from one domain to another, one can either utilize the neighborhood information or learn a direct mapping function. However, all existing methods ignore the high-order connectivity information in cross-…
Cross-domain sentiment analysis is currently a hot topic in the research and engineering areas. One of the most popular frameworks in this field is the domain-invariant representation learning (DIRL) paradigm, which aims to learn a distribution-invariant feature representation across domains. However, in this work, we …
ADVISOR dynamically balances imitation and reinforcement learning to overcome the imitation gap.
Paper proposes LMM-PQS for cross-domain few-shot learning.
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…
Cross-domain collaborative filtering (CF) aims to alleviate data sparsity in single-domain CF by leveraging knowledge transferred from related domains. Many traditional methods focus on enriching compared neighborhood relations in CF directly to address the sparsity problem. In this paper, we propose superhighway const…
Reinforcement learning mimics expert behavior.
Novel methods robustify Gromov-Wasserstein distance for cross-domain alignment.
The cross-domain recommendation technique is an effective way of alleviating the data sparse issue in recommender systems by leveraging the knowledge from relevant domains. Transfer learning is a class of algorithms underlying these techniques. In this paper, we propose a novel transfer learning approach for cross-doma…
Guarantees for third-person imitation learning from offline data.
New metric solves correspondence problem for robotic arm imitation learning.
Learning effective embedding has been proved to be useful in many real-world problems, such as recommender systems, search ranking and online advertisement. However, one of the challenges is data sparsity in learning large-scale item embedding, as users' historical behavior data are usually lacking or insufficient in a…
New method uses bi-level optimization to learn useful representations for imitation learning.
Researchers improved Minecraft game performance using imitation learning.
Cross-domain recommendation has been proposed to transfer user behavior pattern by pooling together the rating data from multiple domains to alleviate the sparsity problem appearing in single rating domains. However, previous models only assume that multiple domains share a latent common rating pattern based on the use…
New self-imitation learning method improves performance in continuous control tasks.
Paper tackles robust imitation learning from noisy demonstrations.
Paper uses Sinkhorn distances to improve imitation learning effectiveness.
Proof shows imitation of expert's reward and solutions in multi-objective optimization.
Cross-domain recommendation has long been one of the major topics in recommender systems. Recently, various deep models have been proposed to transfer the learned knowledge across domains, but most of them focus on extracting abstract transferable features from auxilliary contents, e.g., images and review texts, and th…
We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features, it does not provide an informative reward signal, leading to poor task performanc…
The recent empirical success of unsupervised cross-domain mapping algorithms, between two domains that share common characteristics, is not well-supported by theoretical justifications. This lacuna is especially troubling, given the clear ambiguity in such mappings. We work with adversarial training methods based on IP…
NDI learns from expert demonstrations by estimating occupancy measures.
New method improves imitation learning from expert observations.
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 simplifies and improves imitation learning without adversarial techniques.
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…
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…
Cross-Domain Collaborative Filtering (CDCF) provides a way to alleviate data sparsity and cold-start problems present in recommendation systems by exploiting the knowledge from related domains. Existing CDCF models are either based on matrix factorization or deep neural networks. Either of the techniques in isolation m…
A new model for imputing missing values in time series data across domains.
Proposes a method to imitate active learning heuristics for better performance.
A new method removes policy optimization in adversarial imitation learning.
A new algorithm trains experts to safely guide agents in partially observed environments.
Recent work has demonstrated that problems-- particularly imitation learning and structured prediction-- where a learner's predictions influence the input-distribution it is tested on can be naturally addressed by an interactive approach and analyzed using no-regret online learning. These approaches to imitation learni…
The performance of imitation learning is typically upper-bounded by the performance of the demonstrator. While recent empirical results demonstrate that ranked demonstrations allow for better-than-demonstrator performance, preferences over demonstrations may be difficult to obtain, and little is known theoretically abo…
Imitation learning trains a policy from expert demonstrations. Imitation learning approaches have been designed from various principles, such as behavioral cloning via supervised learning, apprenticeship learning via inverse reinforcement learning, and GAIL via generative adversarial learning. In this paper, we propose…
Proposes a new method for manifold alignment using geometry-regularized twin autoencoders.