The performance of existing supervised neuron segmentation methods is highly dependent on the number of accurate annotations, especially when applied to large scale electron microscopy (EM) data. By extracting semantic information from unlabeled data, self-supervised methods can improve the performance of downstream tasks, among which the mask image model (MIM) has been widely used due to its simplicity and effectiveness in recovering original information from masked images. However, due to the high degree of structural locality in EM images, as well as the existence of considerable noise, many voxels contain little discriminative information, making MIM pretraining inefficient on the neuron segmentation task. To overcome this challenge, we propose a decision-based MIM that utilizes reinforcement learning (RL) to automatically search for optimal image masking ratio and masking strategy. Due to the vast exploration space, using single-agent RL for voxel prediction is impractical. Therefore, we treat each input patch as an agent with a shared behavior policy, allowing for multi-agent collaboration. Furthermore, this multi-agent model can capture dependencies between voxels, which is beneficial for the downstream segmentation task. Experiments conducted on representative EM datasets demonstrate that our approach has a significant advantage over alternative self-supervised methods on the task of neuron segmentation. Code is available at \url{https://github.com/ydchen0806/dbMiM}.

Open-ended algorithms aim to learn new, interesting behaviors forever. That requires a vast environment search space, but there are thus infinitely many possible tasks. Even after filtering for tasks the current agent can learn (i.e., learning progress), countless learnable yet uninteresting tasks remain (e.g., minor variations of previously learned tasks). An Achilles Heel of open-endedness research is the inability to quantify (and thus prioritize) tasks that are not just learnable, but also $\textit{interesting}$ (e.g., worthwhile and novel). We propose solving this problem by $\textit{Open-endedness via Models of human Notions of Interestingness}$ (OMNI). The insight is that we can utilize large (language) models (LMs) as a model of interestingness (MoI), because they $\textit{already}$ internalize human concepts of interestingness from training on vast amounts of human-generated data, where humans naturally write about what they find interesting or boring. We show that LM-based MoIs improve open-ended learning by focusing on tasks that are both learnable $\textit{and interesting}$, outperforming baselines based on uniform task sampling or learning progress alone. This approach has the potential to dramatically advance the ability to intelligently select which tasks to focus on next (i.e., auto-curricula), and could be seen as AI selecting its own next task to learn, facilitating self-improving AI and AI-Generating Algorithms. View website at https://www.jennyzhangzt.com/omni/

In cooperative multi-agent reinforcement learning, a team of agents works together to achieve a common goal. Different environments or tasks may require varying degrees of coordination among agents in order to achieve the goal in an optimal way. The nature of coordination will depend on the properties of the environment -- its spatial layout, distribution of obstacles, dynamics, etc. We term this variation of properties within an environment as heterogeneity. Existing literature has not sufficiently addressed the fact that different environments may have different levels of heterogeneity. We formalize the notions of coordination level and heterogeneity level of an environment and present HECOGrid, a suite of multi-agent RL environments that facilitates empirical evaluation of different MARL approaches across different levels of coordination and environmental heterogeneity by providing a quantitative control over coordination and heterogeneity levels of the environment. Further, we propose a Centralized Training Decentralized Execution learning approach called Stateful Active Facilitator (SAF) that enables agents to work efficiently in high-coordination and high-heterogeneity environments through a differentiable and shared knowledge source used during training and dynamic selection from a shared pool of policies. We evaluate SAF and compare its performance against baselines IPPO and MAPPO on HECOGrid. Our results show that SAF consistently outperforms the baselines across different tasks and different heterogeneity and coordination levels. We release the code for HECOGrid as well as all our experiments.

Designing efficient and accurate numerical solvers for high-dimensional partial differential equations (PDEs) remains a challenging and important topic in computational science and engineering, mainly due to the "curse of dimensionality" in designing numerical schemes that scale in dimension. This paper introduces a new methodology that seeks an approximate PDE solution in the space of functions with finitely many analytic expressions and, hence, this methodology is named the finite expression method (FEX). It is proved in approximation theory that FEX can avoid the curse of dimensionality. As a proof of concept, a deep reinforcement learning method is proposed to implement FEX for various high-dimensional PDEs in different dimensions, achieving high and even machine accuracy with a memory complexity polynomial in dimension and an amenable time complexity. An approximate solution with finite analytic expressions also provides interpretable insights into the ground truth PDE solution, which can further help to advance the understanding of physical systems and design postprocessing techniques for a refined solution.

One of the most fundamental questions in quantitative finance is the existence of continuous-time diffusion models that fit market prices of a given set of options. Traditionally, one employs a mix of intuition, theoretical and empirical analysis to find models that achieve exact or approximate fits. Our contribution is to show how a suitable game theoretical formulation of this problem can help solve this question by leveraging existing developments in modern deep multi-agent reinforcement learning to search in the space of stochastic processes. Our experiments show that we are able to learn local volatility, as well as path-dependence required in the volatility process to minimize the price of a Bermudan option. Our algorithm can be seen as a particle method \textit{\`{a} la} Guyon \textit{et} Henry-Labordere where particles, instead of being designed to ensure $\sigma_{loc}(t,S_t)^2 = \mathbb{E}[\sigma_t^2|S_t]$, are learning RL-driven agents cooperating towards more general calibration targets.

In this paper, a unified framework for exploration in reinforcement learning (RL) is proposed based on an option-critic model. The proposed framework learns to integrate a set of diverse exploration strategies so that the agent can adaptively select the most effective exploration strategy over time to realize a relevant exploration-exploitation trade-off for each given task. The effectiveness of the proposed exploration framework is demonstrated by various experiments in the MiniGrid and Atari environments.

In the rapidly evolving field of serverless computing, efficient function scheduling and resource scaling are critical for optimizing performance and cost. This paper presents a comprehensive review of the application of Deep Reinforcement Learning (DRL) techniques in these areas. We begin by providing an overview of serverless computing, highlighting its benefits and challenges, with a particular focus on function scheduling and resource scaling. We then delve into the principles of deep reinforcement learning (DRL) and its potential for addressing these challenges. A systematic review of recent studies applying DRL to serverless computing is presented, covering various algorithms, models, and performances. Our analysis reveals that DRL, with its ability to learn and adapt from an environment, shows promising results in improving the efficiency of function scheduling and resource scaling in serverless computing. However, several challenges remain, including the need for more realistic simulation environments, handling of cold starts, and the trade-off between learning time and scheduling performance. We conclude by discussing potential future directions for this research area, emphasizing the need for more robust DRL models, better benchmarking methods, and the exploration of multi-agent reinforcement learning for more complex serverless architectures. This review serves as a valuable resource for researchers and practitioners aiming to understand and advance the application of DRL in serverless computing.

Behavioural metrics have been shown to be an effective mechanism for constructing representations in reinforcement learning. We present a novel perspective on behavioural metrics for Markov decision processes via the use of positive definite kernels. We leverage this new perspective to define a new metric that is provably equivalent to the recently introduced MICo distance (Castro et al., 2021). The kernel perspective further enables us to provide new theoretical results, which has so far eluded prior work. These include bounding value function differences by means of our metric, and the demonstration that our metric can be provably embedded into a finite-dimensional Euclidean space with low distortion error. These are two crucial properties when using behavioural metrics for reinforcement learning representations. We complement our theory with strong empirical results that demonstrate the effectiveness of these methods in practice.

In value-based deep reinforcement learning with replay memories, the batch size parameter specifies how many transitions to sample for each gradient update. Although critical to the learning process, this value is typically not adjusted when proposing new algorithms. In this work we present a broad empirical study that suggests {\em reducing} the batch size can result in a number of significant performance gains; this is surprising, as the general tendency when training neural networks is towards larger batch sizes for improved performance. We complement our experimental findings with a set of empirical analyses towards better understanding this phenomenon.

We introduce HandMeThat, a benchmark for a holistic evaluation of instruction understanding and following in physical and social environments. While previous datasets primarily focused on language grounding and planning, HandMeThat considers the resolution of human instructions with ambiguities based on the physical (object states and relations) and social (human actions and goals) information. HandMeThat contains 10,000 episodes of human-robot interactions. In each episode, the robot first observes a trajectory of human actions towards her internal goal. Next, the robot receives a human instruction and should take actions to accomplish the subgoal set through the instruction. In this paper, we present a textual interface for our benchmark, where the robot interacts with a virtual environment through textual commands. We evaluate several baseline models on HandMeThat, and show that both offline and online reinforcement learning algorithms perform poorly on HandMeThat, suggesting significant room for future work on physical and social human-robot communications and interactions.