Experience replay (ER) used in (deep) reinforcement learning is considered to be applicable only to off-policy algorithms. However, there have been some cases in which ER has been applied for on-policy algorithms, suggesting that off-policyness might be a sufficient condition for applying ER. This paper reconsiders more strict "experience replayable conditions" (ERC) and proposes the way of modifying the existing algorithms to satisfy ERC. To this end, instability of policy improvements is assumed to be a key in ERC. The instability factors are revealed from the viewpoint of metric learning as i) repulsive forces from negative samples and ii) replays of inappropriate experiences. Accordingly, the corresponding stabilization tricks are derived. As a result, it is confirmed through numerical simulations that the proposed stabilization tricks make ER applicable to an advantage actor-critic, an on-policy algorithm. In addition, its learning performance is comparable to that of a soft actor-critic, a state-of-the-art off-policy algorithm.

We consider the problem of sampling from a discrete and structured distribution as a sequential decision problem, where the objective is to find a stochastic policy such that objects are sampled at the end of this sequential process proportionally to some predefined reward. While we could use maximum entropy Reinforcement Learning (MaxEnt RL) to solve this problem for some distributions, it has been shown that in general, the distribution over states induced by the optimal policy may be biased in cases where there are multiple ways to generate the same object. To address this issue, Generative Flow Networks (GFlowNets) learn a stochastic policy that samples objects proportionally to their reward by approximately enforcing a conservation of flows across the whole Markov Decision Process (MDP). In this paper, we extend recent methods correcting the reward in order to guarantee that the marginal distribution induced by the optimal MaxEnt RL policy is proportional to the original reward, regardless of the structure of the underlying MDP. We also prove that some flow-matching objectives found in the GFlowNet literature are in fact equivalent to well-established MaxEnt RL algorithms with a corrected reward. Finally, we study empirically the performance of multiple MaxEnt RL and GFlowNet algorithms on multiple problems involving sampling from discrete distributions.

Given a network, allocating resources at clusters level, rather than at each node, enhances efficiency in resource allocation and usage. In this paper, we study the problem of finding fully connected disjoint clusters to minimize the intra-cluster distances and maximize the number of nodes assigned to the clusters, while also ensuring that no two nodes within a cluster exceed a threshold distance. While the problem can easily be formulated using a binary linear model, traditional combinatorial optimization solvers struggle when dealing with large-scale instances. We propose an approach to solve this constrained clustering problem via reinforcement learning. Our method involves training an agent to generate both feasible and (near) optimal solutions. The agent learns problem-specific heuristics, tailored to the instances encountered in this task. In the results section, we show that our algorithm finds near optimal solutions, even for large scale instances.

We study the robustness of deep reinforcement learning algorithms against distribution shifts within contextual multi-stage stochastic combinatorial optimization problems from the operations research domain. In this context, risk-sensitive algorithms promise to learn robust policies. While this field is of general interest to the reinforcement learning community, most studies up-to-date focus on theoretical results rather than real-world performance. With this work, we aim to bridge this gap by formally deriving a novel risk-sensitive deep reinforcement learning algorithm while providing numerical evidence for its efficacy. Specifically, we introduce discrete Soft Actor-Critic for the entropic risk measure by deriving a version of the Bellman equation for the respective Q-values. We establish a corresponding policy improvement result and infer a practical algorithm. We introduce an environment that represents typical contextual multi-stage stochastic combinatorial optimization problems and perform numerical experiments to empirically validate our algorithm's robustness against realistic distribution shifts, without compromising performance on the training distribution. We show that our algorithm is superior to risk-neutral Soft Actor-Critic as well as to two benchmark approaches for robust deep reinforcement learning. Thereby, we provide the first structured analysis on the robustness of reinforcement learning under distribution shifts in the realm of contextual multi-stage stochastic combinatorial optimization problems.

Crowdsourced delivery platforms face complex scheduling challenges to match couriers and customer orders. We consider two types of crowdsourced couriers, namely, committed and occasional couriers, each with different compensation schemes. Crowdsourced delivery platforms usually schedule committed courier shifts based on predicted demand. Therefore, platforms may devise an offline schedule for committed couriers before the planning period. However, due to the unpredictability of demand, there are instances where it becomes necessary to make online adjustments to the offline schedule. In this study, we focus on the problem of dynamically adjusting the offline schedule through shift extensions for committed couriers. This problem is modeled as a sequential decision process. The objective is to maximize platform profit by determining the shift extensions of couriers and the assignments of requests to couriers. To solve the model, a Deep Q-Network (DQN) learning approach is developed. Comparing this model with the baseline policy where no extensions are allowed demonstrates the benefits that platforms can gain from allowing shift extensions in terms of reward, reduced lost order costs, and lost requests. Additionally, sensitivity analysis showed that the total extension compensation increases in a nonlinear manner with the arrival rate of requests, and in a linear manner with the arrival rate of occasional couriers. On the compensation sensitivity, the results showed that the normal scenario exhibited the highest average number of shift extensions and, consequently, the fewest average number of lost requests. These findings serve as evidence of the successful learning of such dynamics by the DQN algorithm.

Since these efficient models do not share sequence length We discover that the recurrent update of limitations with past models, we question whether the use these models is a monoid, leading us to formally of segments is still necessary. After highlighting the empirical define a novel memory monoid framework. We and theoretical shortcomings of segments, we propose revisit the traditional approach to batching in recurrent an alternative batching method. Our method improves RL, highlighting both theoretical and empirical sample efficiency across various tasks and memory models, deficiencies. Leveraging the properties while simplifying implementation. of memory monoids, we propose a new batching method that improves sample efficiency, increases the return, and simplifies the implementation Contributions of recurrent loss functions in RL. 1. We propose the memory monoid, a unifying framework for efficient sequence models.

The search for a general model that can operate seamlessly across multiple domains remains a key goal in machine learning research. The prevailing methodology in Reinforcement Learning (RL) typically limits models to a single task within a unimodal framework, a limitation that contrasts with the broader vision of a versatile, multi-domain model. In this paper, we present Jack of All Trades (JAT), a transformer-based model with a unique design optimized for handling sequential decision-making tasks and multimodal data types. The JAT model demonstrates its robust capabilities and versatility by achieving strong performance on very different RL benchmarks, along with promising results on Computer Vision (CV) and Natural Language Processing (NLP) tasks, all using a single set of weights. The JAT model marks a significant step towards more general, cross-domain AI model design, and notably, it is the first model of its kind to be fully open-sourced (see https://huggingface.co/jat-project/jat), including a pioneering general-purpose dataset.

When Reinforcement Learning (RL) agents are deployed in practice, they might impact their environment and change its dynamics. Ongoing research attempts to formally model this phenomenon and to analyze learning algorithms in these models. To this end, we propose a framework where the current environment depends on the deployed policy as well as its previous dynamics. This is a generalization of Performative RL (PRL) [Mandal et al., 2023]. Unlike PRL, our framework allows to model scenarios where the environment gradually adjusts to a deployed policy. We adapt two algorithms from the performative prediction literature to our setting and propose a novel algorithm called Mixed Delayed Repeated Retraining (MDRR). We provide conditions under which these algorithms converge and compare them using three metrics: number of retrainings, approximation guarantee, and number of samples per deployment. Unlike previous approaches, MDRR combines samples from multiple deployments in its training. This makes MDRR particularly suitable for scenarios where the environment's response strongly depends on its previous dynamics, which are common in practice. We experimentally compare the algorithms using a simulation-based testbed and our results show that MDRR converges significantly faster than previous approaches.

This paper introduces a reinforcement learning approach to optimize the Stochastic Vehicle Routing Problem with Time Windows (SVRP), focusing on reducing travel costs in goods delivery. We develop a novel SVRP formulation that accounts for uncertain travel costs and demands, alongside specific customer time windows. An attention-based neural network trained through reinforcement learning is employed to minimize routing costs. Our approach addresses a gap in SVRP research, which traditionally relies on heuristic methods, by leveraging machine learning. The model outperforms the Ant-Colony Optimization algorithm, achieving a 1.73% reduction in travel costs. It uniquely integrates external information, demonstrating robustness in diverse environments, making it a valuable benchmark for future SVRP studies and industry application.

Policy Optimization (PO) algorithms are a class of methods in Reinforcement Learning(RL; Sutton and Barto, 2018; Mannor et al., 2022) where the agent's policy is iteratively updated according to the (possibly preconditioned) gradient of the value function w.r.t.