Search Results for author:
Found 20 papers, 7 papers with code
Distributional Off-Policy Evaluation for Slate Recommendations
Prior work has developed estimators that leverage the structure in slates to estimate the expected off-policy performance, but the estimation of the entire performance distribution remains elusive.
Coagent Networks: Generalized and Scaled
However, the coagent framework is not just an alternative to BDL; the two approaches can be blended: BDL can be combined with coagent learning rules to create architectures with the advantages of both approaches.
Explaining RL Decisions with Trajectories
To do so, we encode trajectories in offline training data individually as well as collectively (encoding a set of trajectories).
Personalized Detection of Cognitive Biases in Actions of Users from Their Logs: Anchoring and Recency Biases
The recognition of cognitive bias in computer science is largely in the domain of information retrieval, and bias is identified at an aggregate level with the help of annotated data.
Smoothed Online Combinatorial Optimization Using Imperfect Predictions
Smoothed online combinatorial optimization considers a learner who repeatedly chooses a combinatorial decision to minimize an unknown changing cost function with a penalty on switching decisions in consecutive rounds.
Off-Policy Evaluation in Embedded Spaces
Second, many recommendation systems are not probabilistic and so having access to logging and target policy densities may not be feasible.
Constraint Sampling Reinforcement Learning: Incorporating Expertise For Faster Learning
Online reinforcement learning (RL) algorithms are often difficult to deploy in complex human-facing applications as they may learn slowly and have poor early performance.
Edge-Compatible Reinforcement Learning for Recommendations
In this work, we build on asynchronous coagent policy gradient algorithms \citep{kostas2020asynchronous} to propose a principled solution to this problem.
Multiscale Manifold Warping
Many real-world applications require aligning two temporal sequences, including bioinformatics, handwriting recognition, activity recognition, and human-robot coordination.
Towards Safe Policy Improvement for Non-Stationary MDPs
Many real-world sequential decision-making problems involve critical systems with financial risks and human-life risks.
Reinforcement Learning for Strategic Recommendations
Strategic recommendations (SR) refer to the problem where an intelligent agent observes the sequential behaviors and activities of users and decides when and how to interact with them to optimize some long-term objectives, both for the user and the business.
Optimizing for the Future in Non-Stationary MDPs
Most reinforcement learning methods are based upon the key assumption that the transition dynamics and reward functions are fixed, that is, the underlying Markov decision process is stationary.
Lifelong Learning with a Changing Action Set
have been well-studied in the lifelong learning literature, the setting where the action set changes remains unaddressed.
Reinforcement Learning When All Actions are Not Always Available
The Markov decision process (MDP) formulation used to model many real-world sequential decision making problems does not efficiently capture the setting where the set of available decisions (actions) at each time step is stochastic.
Learning Action Representations for Reinforcement Learning
Most model-free reinforcement learning methods leverage state representations (embeddings) for generalization, but either ignore structure in the space of actions or assume the structure is provided a priori.
Scalar Posterior Sampling with Applications
Our algorithm termed deterministic schedule PSRL (DS-PSRL) is efficient in terms of time, sample, and space complexity.
Posterior Sampling for Large Scale Reinforcement Learning
Our algorithm termed deterministic schedule PSRL (DS-PSRL) is efficient in terms of time, sample, and space complexity.
Personalized Advertisement Recommendation: A Ranking Approach to Address the Ubiquitous Click Sparsity Problem
We study the problem of personalized advertisement recommendation (PAR), which consist of a user visiting a system (website) and the system displaying one of $K$ ads to the user.
Graphical Model Sketch
Graphical models are a popular approach to modeling structured data but they are unsuitable for high-cardinality variables.
Policy Evaluation Using the Ω-Return
The benefit of the Ω-return is that it accounts for the correlation of different length returns.
