Neural Information Processing Systems http://nips.cc/

One weakness of Monte Carlo Tree Search (MCTS) is its sample efficiency which can be addressed by building and using state and/or action abstractions in parallel to the tree search such that information can be shared among nodes of the same layer. The primary usage of abstractions for MCTS is to enhance the Upper Confidence Bound (UCB) value during the tree policy by aggregating visits and returns of an abstract node. However, this direct usage of abstractions does not take the case into account where multiple actions with the same parent might be in the same abstract node, as these would then all have the same UCB value, thus requiring a tiebreak rule. In state-of-the-art abstraction algorithms such as pruned On the Go Abstractions (pruned OGA), this case has not been noticed, and a random tiebreak rule was implicitly chosen. In this paper, we propose and empirically evaluate several alternative intra-abstraction policies, several of which outperform the random policy across a majority of environments and parameter settings.

Interpretable reinforcement learning policies are essential for high-stakes decision-making, yet optimizing decision tree policies in Markov Decision Processes (MDPs) remains challenging. We propose SPOT, a novel method for computing decision tree policies, which formulates the optimization problem as a mixed-integer linear program (MILP). To enhance efficiency, we employ a reduced-space branch-and-bound approach that decouples the MDP dynamics from tree-structure constraints, enabling efficient parallel search. This significantly improves runtime and scalability compared to previous methods. Our approach ensures that each iteration yields the optimal decision tree. Experimental results on standard benchmarks demonstrate that SPOT achieves substantial speedup and scales to larger MDPs with a significantly higher number of states. The resulting decision tree policies are interpretable and compact, maintaining transparency without compromising performance. These results demonstrate that our approach simultaneously achieves interpretability and scalability, delivering high-quality policies an order of magnitude faster than existing approaches.

Neural Information Processing Systems http://nips.cc/

We create a computationally tractable algorithm for contextual bandits with continuous actions having unknown structure.

Rationing of healthcare resources is a challenging decision that policy makers and providers may be forced to make during a pandemic, natural disaster, or mass casualty event. Well-defined guidelines to triage scarce life-saving resources must be designed to promote transparency, trust, and consistency. To facilitate buy-in and use during high-stress situations, these guidelines need to be interpretable and operational. We propose a novel data-driven model to compute interpretable triage guidelines based on policies for Markov Decision Process that can be represented as simple sequences of decision trees ("tree policies"). In particular, we characterize the properties of optimal tree policies and present an algorithm based on dynamic programming recursions to compute good tree policies. We utilize this methodology to obtain simple, novel triage guidelines for ventilator allocations for COVID-19 patients, based on real patient data from Montefiore hospitals. We also compare the performance of our guidelines to the official New York State guidelines that were developed in 2015 (well before the COVID-19 pandemic). Our empirical study shows that the number of excess deaths associated with ventilator shortages could be reduced significantly using our policy. Our work highlights the limitations of the existing official triage guidelines, which need to be adapted specifically to COVID-19 before being successfully deployed.

We present a new Monte Carlo Tree Search (MCTS) algorithm to solve the stochastic orienteering problem with chance constraints, i.e., a version of the problem where travel costs are random, and one is assigned a bound on the tolerable probability of exceeding the budget. The algorithm we present is online and anytime, i.e., it alternates planning and execution, and the quality of the solution it produces increases as the allowed computational time increases. Differently from most former MCTS algorithms, for each action available in a state the algorithm maintains estimates of both its value and the probability that its execution will eventually result in a violation of the chance constraint. Then, at action selection time, our proposed solution prunes away trajectories that are estimated to violate the failure probability. Extensive simulation results show that this approach can quickly produce high-quality solutions and is competitive with the optimal but time-consuming solution.

In the field of high-performance computing (HPC), there has been recent exploration into the use of deep reinforcement learning for cluster scheduling (DRL scheduling), which has demonstrated promising outcomes. However, a significant challenge arises from the lack of interpretability in deep neural networks (DNN), rendering them as black-box models to system managers. This lack of model interpretability hinders the practical deployment of DRL scheduling. In this work, we present a framework called IRL (Interpretable Reinforcement Learning) to address the issue of interpretability of DRL scheduling. The core idea is to interpret DNN (i.e., the DRL policy) as a decision tree by utilizing imitation learning. Unlike DNN, decision tree models are non-parametric and easily comprehensible to humans. To extract an effective and efficient decision tree, IRL incorporates the Dataset Aggregation (DAgger) algorithm and introduces the notion of critical state to prune the derived decision tree. Through trace-based experiments, we demonstrate that IRL is capable of converting a black-box DNN policy into an interpretable rulebased decision tree while maintaining comparable scheduling performance. Additionally, IRL can contribute to the setting of rewards in DRL scheduling.

When we exercise sequences of actions, their execution becomes more fluent and precise. Here, we consider the possibility that exercised action sequences can also be used to make planning faster and more accurate by focusing expansion of the search tree on paths that have been frequently used in the past, and by reducing deep planning problems to shallow ones via multi-step jumps in the tree. To capture such sequences, we use a flexible Bayesian action chunking mechanism which finds and exploits statistically reliable structure at different scales. This gives rise to shorter or longer routines that can be embedded into a Monte-Carlo tree search planner. We show the benefits of this scheme using a physical construction task patterned after tangrams.