Posts

FedSkill: Privacy Preserved Interpretable Skill Learning via Imitation

FedSkill: Privacy Preserved Interpretable Skill Learning via Imitation Imitation learning that replicates experts’ skills via their demonstrations has shown significant success in various decision-making tasks. However, two critical challenges still hinder the deployment of imitation learning techniques in real-world application scenarios. First, existing methods lack the intrinsic interpretability to explicitly explain the underlying rationale of the learned skill and thus making learned policy untrustworthy. Second, due to the scarcity of expert demonstrations from each end user (client), learning a policy based on different data silos is necessary but challenging in privacy-sensitive applications such as finance and healthcare. To this end, we present a privacy-preserved interpretable skill learning framework (FedSkill) that enables global policy learning to incorporate data from different sources and provides explainable interpretations to each local user without violating privacy and data sovereignty. Specifically, our proposed interpretable skill learning model can capture the varying patterns in the trajectories of expert demonstrations, and extract prototypical information as skills that provide implicit guidance for policy learning and explicit explanations in the reasoning process. Moreover, we design a novel aggregation mechanism coupled with the based skill learning model to preserve global information utilization and maintain local interpretability under the federated framework. Thoroughly experiments on three datasets and empirical studies demonstrate that our proposed FedSkill framework not only outperforms state-of-the-art imitation learning methods but also exhibits good interpretability under a federated setting. Our proposed FedSkill framework is the first attempt to bridge the gaps among federated learning, interpretable machine learning, and imitation learning.

Interpretable Skill Learning for Dynamic Treatment Regimes through Imitation

Interpretable Skill Learning for Dynamic Treatment Regimes through Imitation Imitation learning that mimics experts’ skills from their demonstrations has shown great success in discovering dynamic treatment regimes, i.e., the optimal decision rules to treat an individual patient based on related evolving treatment and covariate history. Existing imitation learning methods, however, still lack the capability to interpret the underlying rationales of the learned policy in a faithful way. Moreover, since dynamic treatment regimes for patients often exhibit varying patterns, i.e., symptoms that transit from one to another, the flat policy learned by a vanilla imitation learning method is typically undesired. To this end, we propose an Interpretable Skill Learning (ISL) framework to resolve the aforementioned challenges for dynamic treatment regimes through imitation. The key idea is to model each segment of experts’ demonstrations with a prototype layer and integrate it with the imitation learning layer to enhance the interpretation capability. On one hand, the ISL framework is able to provide interpretable explanations by matching the prototype to exemplar segments during the inference stage, which enables doctors to perform reasoning of the learned demonstrations based on human-understandable patient symptoms and lab results. On the other hand, the obtained skill embedding consisting of prototypes serves as conditional information to the imitation learning layer, which implicitly guides the policy network to provide a more accurate demonstration when the patients’ state switches from one stage to another. Thoroughly empirical studies demonstrate that our proposed ISL technique can achieve better performance than state-of-the-art methods. Moreover, the proposed ISL framework also exhibits good interpretability which cannot be observed in existing methods.

Dynamic Causal Discovery in Imitation Learning

Dynamic Causal Discovery in Imitation Learning Using deep reinforcement learning (DRL) to recover expert policies via imitation has been found to be promising in a wide range of applications. However, it remains a difficult task to interpret the control policy learned by the agent. Difficulties mainly come from two aspects: 1) agents in DRL are usually implemented as deep neural networks (DNNs), which are black-box models and lack in interpretability, 2) the latent causal mechanism behind agents’ decisions may vary along the trajectory, rather than staying static throughout time steps. To address these difficulties, in this paper, we propose a self-explaining imitation framework, which can expose causal relations among states and action variables behind its decisions. Specifically, a dynamic causal discovery module is designed to extract the causal graph basing on historical trajectory and current states at each time step, and a causality encoding module is designed to model the interactions among variables with discovered causal edges. After encoding causality into variable embeddings, a prediction model conducts the imitation learning on top of obtained representations. These three components are trained end-to-end, and discovered causal edges can provide interpretations on rules captured by the agent. Comprehensive experiments are conducted on the simulation dataset to analyze its causal discovery capacity, and we further test it on a real-world medical dataset MIMIC-IV. Experimental results demonstrate its potential of providing explanations behind decisions.

Hierarchical Imitation Learning with Contextual Bandits for Dynamic Treatment Regimes

Hierarchical Imitation Learning with Contextual Bandits for Dynamic Treatment Regimes Imitation learning has been proved to be effective in mimicking experts’ behaviors from their demonstrations without access to explicit reward signals. Meanwhile, complex tasks, e.g., dynamic treatment regimes for patients with comorbidities, often suggest significant variability in expert demonstrations with multiple sub-tasks. In these cases, it could be difficult to use a single flat policy to handle tasks of hierarchical structures. In this paper, we propose the hierarchical imitation learning model, HIL, to jointly learn latent high-level policies and sub-policies (for individual sub-tasks) from expert demonstrations without prior knowledge. First, HIL learns sub-policies by imitating expert trajectories with the sub-task switching guidance from high-level policies. Second, HIL collects the feedback from its sub-policies to optimize high-level policies, which is modeled as a contextual multi-arm bandit that sequentially selects the best sub-policies at each time step based on the contextual information derived from demonstrations. Compared with state-of-the-art baselines on real-world medical data, HIL improves the likelihood of patient survival and provides better dynamic treatment regimes with the exploitation of hierarchical structures in expert demonstrations.

Adversarial Cooperative Imitation Learning for Dynamic Treatment Regimes

Adversarial Cooperative Imitation Learning for Dynamic Treatment Regimes Recent developments in discovering dynamic treatment regimes (DTRs) have heightened the importance of deep reinforcement learning (DRL) which are used to recover the doctor’s treatment policies. However, existing DRL-based methods expose the following limitations: 1) supervised methods based on behavior cloning suffer from compounding errors, 2) the self-defined reward signals in reinforcement learning models are either too sparse or need clinical guidance, 3) only positive trajectories (e.g. survived patients) are considered in current imitation learning models, with negative trajectories (e.g. deceased patients) been largely ignored, which are examples of what not to do and could help the learned policy avoid repeating mistakes. To address these limitations, in this paper, we propose the adversarial cooperative imitation learning model, ACIL, to deduce the optimal dynamic treatment regimes that mimics the positive trajectories while differs from the negative trajectories. Specifically, two discriminators are used to help achieve this goal: an adversarial discriminator is designed to minimize the discrepancies between the trajectories generated from the policy and the positive trajectories, and a cooperative discriminator is used to distinguish the negative trajectories from the positive and generated trajectories. The reward signals from the discriminators are utilized to refine the policy for dynamic treatment regimes. Experiments on the publicly real-world medical data demonstrate that ACIL improves the likelihood of patient survival and provides better dynamic treatment regimes with the exploitation of information from both positive and negative trajectories.