# Offline Contextual Bandits in the Presence of New Actions

arXiv: https://arxiv.org/abs/2605.18509 · HTML: https://mlsanity.com/paper/2605.18509/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 18 May 2026.

## Builds on (most cited first, 24 of 24)

- [Doubly Robust Policy Evaluation and Optimization](https://mlsanity.com/paper/1503.02834/) (2015)
- [More Robust Doubly Robust Off-policy Evaluation](https://mlsanity.com/paper/1802.03493/) (2018)
- [Optimal and Adaptive Off-policy Evaluation in Contextual Bandits](https://mlsanity.com/paper/1612.01205/) (2016)
- [Off-policy evaluation for slate recommendation](https://mlsanity.com/paper/1605.04812/) (2016)
- [A Review of Off-Policy Evaluation in Reinforcement Learning](https://mlsanity.com/paper/2212.06355/) (2022)
- [Offline A/B testing for Recommender Systems](https://mlsanity.com/paper/1801.07030/) (2018)
- [KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems](https://mlsanity.com/paper/2202.10842/) (2022)
- [Doubly robust off-policy evaluation with shrinkage](https://mlsanity.com/paper/1907.09623/) (2019)
- [Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation](https://mlsanity.com/paper/2008.07146/) (2020)
- [Off-policy Bandits with Deficient Support](https://mlsanity.com/paper/2006.09438/) (2020)
- [Policy Evaluation and Optimization with Continuous Treatments](https://mlsanity.com/paper/1802.06037/) (2018)
- [Off-Policy Evaluation for Large Action Spaces via Embeddings](https://mlsanity.com/paper/2202.06317/) (2022)
- [Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling](https://mlsanity.com/paper/2305.08062/) (2023)
- [Evaluating the Robustness of Off-Policy Evaluation](https://mlsanity.com/paper/2108.13703/) (2021)
- [Optimal Off-Policy Evaluation from Multiple Logging Policies](https://mlsanity.com/paper/2010.11002/) (2020)
- [Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model](https://mlsanity.com/paper/2202.01562/) (2022)
- [Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction](https://mlsanity.com/paper/2402.02171/) (2024)
- [Off-Policy Evaluation of Ranking Policies under Diverse User Behavior](https://mlsanity.com/paper/2306.15098/) (2023)
- [POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition](https://mlsanity.com/paper/2402.06151/) (2024)
- [Control Variates for Slate Off-Policy Evaluation](https://mlsanity.com/paper/2106.07914/) (2021)
- [Long-term Off-Policy Evaluation and Learning](https://mlsanity.com/paper/2404.15691/) (2024)
- [Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits](https://mlsanity.com/paper/2408.11202/) (2024)
- [Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It](https://mlsanity.com/paper/2404.15084/) (2024)
- [Distributional Off-Policy Evaluation for Slate Recommendations](https://mlsanity.com/paper/2308.14165/) (2023)

## Abstract (arXiv)

Automated decision-making algorithms drive applications such as recommendation systems and search engines. These algorithms often rely on off-policy contextual bandits or off-policy learning (OPL). Conventionally, OPL selects actions that maximize the expected reward from an existing action set. However, in many real-world scenarios, actions, such as news articles or video content, change continuously, and the action space evolves over time after data collection. We define actions introduced after deploying the logging policy as new actions and focus on OPL with new actions. Existing OPL methods identify optimal actions from the existing set effectively but cannot learn and select new actions because no relevant data are logged. To address this limitation, we propose a new OPL method that leverages action features. We first introduce the Local Combination PseudoInverse (LCPI) estimator for the policy gradient, generalizing the PseudoInverse estimator initially proposed for off-policy evaluation of slate bandits. LCPI controls the trade-off between reward-modeling condition and the condition for data collection regarding the action features, capturing the interaction effects among different dimensions of action features. Furthermore, we propose a generalized algorithm called Policy Optimization for Effective New Actions (PONA), which integrates LCPI, a component specialized for new action selection, with Doubly Robust (DR), which excels at learning within existing actions. We define PONA as a weighted sum of the LCPI and DR estimators, optimizing both the selection of existing and new actions, and allowing the proportion of new action selections to be adjusted by the weight parameter. Through extensive experiments, we demonstrate that PONA efficiently selects new actions while maintaining the overall policy performance as opposed to most existing methods that cannot select new actions.