CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies

• URL: http://arxiv.org/abs/2408.12004v1
• Date: Wed, 21 Aug 2024 21:38:03 GMT
• Title: CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies
• Authors: Brian M Cho, Ana-Roxana Pop, Kyra Gan, Sam Corbett-Davies, Israel Nir, Ariel Evnine, Nathan Kallus,
• Abstract summary: We focus on threshold policies, a ubiquitous class of policies with applications in economics, healthcare, and digital advertising. Existing methods rely on potentially underpowered safety checks and limit the opportunities for finding safe improvements. We show that in adversarial settings, our approach controls the rate of adopting a policy worse than the baseline to the pre-specified error level.
• Score: 30.57323631122579
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When modifying existing policies in high-risk settings, it is often necessary to ensure with high certainty that the newly proposed policy improves upon a baseline, such as the status quo. In this work, we consider the problem of safe policy improvement, where one only adopts a new policy if it is deemed to be better than the specified baseline with at least pre-specified probability. We focus on threshold policies, a ubiquitous class of policies with applications in economics, healthcare, and digital advertising. Existing methods rely on potentially underpowered safety checks and limit the opportunities for finding safe improvements, so too often they must revert to the baseline to maintain safety. We overcome these issues by leveraging the most powerful safety test in the asymptotic regime and allowing for multiple candidates to be tested for improvement over the baseline. We show that in adversarial settings, our approach controls the rate of adopting a policy worse than the baseline to the pre-specified error level, even in moderate sample sizes. We present CSPI and CSPI-MT, two novel heuristics for selecting cutoff(s) to maximize the policy improvement from baseline. We demonstrate through both synthetic and external datasets that our approaches improve both the detection rates of safe policies and the realized improvement, particularly under stringent safety requirements and low signal-to-noise conditions.

Related papers

• Embedding Safety into RL: A New Take on Trust Region Methods [1.5733417396701983]
  Reinforcement Learning (RL) agents are able to solve a wide variety of tasks but are prone to unsafe behaviors. We propose Constrained Trust Region Policy Optimization (C-TRPO), a novel approach that modifies the geometry of the policy space based on the safety constraints.
  arXiv  Detail & Related papers  (2024-11-05T09:55:50Z)
• Hallucinated Adversarial Control for Conservative Offline Policy Evaluation [64.94009515033984]
  We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, we seek to obtain a (tight) lower bound on a policy's performance. We introduce HAMBO, which builds on an uncertainty-aware learned model of the transition dynamics. We prove that the resulting COPE estimates are valid lower bounds, and, under regularity conditions, show their convergence to the true expected return.
  arXiv  Detail & Related papers  (2023-03-02T08:57:35Z)
• Local Policy Improvement for Recommender Systems [8.617221361305901]
  We show how to train a new policy given data collected from a previously-deployed policy. We suggest an alternative approach of local policy improvement without off-policy correction. This local policy improvement paradigm is ideal for recommender systems, as previous policies are typically of decent quality and policies are updated frequently.
  arXiv  Detail & Related papers  (2022-12-22T00:47:40Z)
• Safe Reinforcement Learning via Confidence-Based Filters [78.39359694273575]
  We develop a control-theoretic approach for certifying state safety constraints for nominal policies learned via standard reinforcement learning techniques. We provide formal safety guarantees, and empirically demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2022-07-04T11:43:23Z)
• Memory-Constrained Policy Optimization [59.63021433336966]
  We introduce a new constrained optimization method for policy gradient reinforcement learning. We form a second trust region through the construction of another virtual policy that represents a wide range of past policies. We then enforce the new policy to stay closer to the virtual policy, which is beneficial in case the old policy performs badly.
  arXiv  Detail & Related papers  (2022-04-20T08:50:23Z)
• An Alternate Policy Gradient Estimator for Softmax Policies [36.48028448548086]
  We propose a novel policy gradient estimator for softmax policies. Our analysis and experiments, conducted on bandits and classical MDP benchmarking tasks, show that our estimator is more robust to policy saturation.
  arXiv  Detail & Related papers  (2021-12-22T02:01:19Z)
• Safe Policy Learning through Extrapolation: Application to Pre-trial Risk Assessment [0.0]
  We develop a robust optimization approach that partially identifies the expected utility of a policy, and then finds an optimal policy. We extend this approach to common and important settings where humans make decisions with the aid of algorithmic recommendations. We derive new classification and recommendation rules that retain the transparency and interpretability of the existing risk assessment instrument.
  arXiv  Detail & Related papers  (2021-09-22T00:52:03Z)
• Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs [71.47895794305883]
  We study the problem of Safe Policy Improvement (SPI) under constraints in the offline Reinforcement Learning setting. We present an SPI for this RL setting that takes into account the preferences of the algorithm's user for handling the trade-offs for different reward signals.
  arXiv  Detail & Related papers  (2021-05-31T21:04:21Z)
• Offline Policy Selection under Uncertainty [113.57441913299868]
  We consider offline policy selection as learning preferences over a set of policy prospects given a fixed experience dataset. Access to the full distribution over one's belief of the policy value enables more flexible selection algorithms under a wider range of downstream evaluation metrics. We show how BayesDICE may be used to rank policies with respect to any arbitrary downstream policy selection metric.
  arXiv  Detail & Related papers  (2020-12-12T23:09:21Z)
• Stable Policy Optimization via Off-Policy Divergence Regularization [50.98542111236381]
  Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are among the most successful policy gradient approaches in deep reinforcement learning (RL) We propose a new algorithm which stabilizes the policy improvement through a proximity term that constrains the discounted state-action visitation distribution induced by consecutive policies to be close to one another. Our proposed method can have a beneficial effect on stability and improve final performance in benchmark high-dimensional control tasks.
  arXiv  Detail & Related papers  (2020-03-09T13:05:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.