Decentralized cooperative multi-agent deep reinforcement learning (MARL) can be a versatile learning framework, particularly in scenarios where centralized training is either not possible or not practical. One of the critical challenges in decentralized deep MARL is the non-stationarity of the learning environment when multiple agents are learning concurrently. A commonly used and efficient scheme for decentralized MARL is independent learning in which agents concurrently update their policies independently of each other. We first show that independent learning does not always converge, while sequential learning where agents update their policies one after another in a sequence is guaranteed to converge to an agent-by-agent optimal solution. In sequential learning, when one agent updates its policy, all other agent's policies are kept fixed, alleviating the challenge of non-stationarity due to simultaneous updates in other agents' policies. However, it can be slow because only one agent is learning at any time. Therefore it might also not always be practical. In this work, we propose a decentralized cooperative MARL algorithm based on multi-timescale learning. In multi-timescale learning, all agents learn simultaneously, but at different learning rates. In our proposed method, when one agent updates its policy, other agents are allowed to update their policies as well, but at a slower rate. This speeds up sequential learning, while also minimizing non-stationarity caused by other agents updating concurrently. Multi-timescale learning outperforms state-of-the-art decentralized learning methods on a set of challenging multi-agent cooperative tasks in the epymarl(Papoudakis et al., 2020) benchmark. This can be seen as a first step towards more general decentralized cooperative deep MARL methods based on multi-timescale learning.

Robots have been successfully used to perform tasks with high precision. In real-world environments with sparse rewards and multiple goals, learning is still a major challenge and Reinforcement Learning (RL) algorithms fail to learn good policies. Training in simulation environments and then fine-tuning in the real world is a common approach. However, adapting to the real-world setting is a challenge. In this paper, we present a method named Ready for Production Hierarchical RL (ReProHRL) that divides tasks with hierarchical multi-goal navigation guided by reinforcement learning. We also use object detectors as a pre-processing step to learn multi-goal navigation and transfer it to the real world. Empirical results show that the proposed ReProHRL method outperforms the state-of-the-art baseline in simulation and real-world environments in terms of both training time and performance. Although both methods achieve a 100% success rate in a simple environment for single goal-based navigation, in a more complex environment and multi-goal setting, the proposed method outperforms the baseline by 18% and 5%, respectively. For the real-world implementation and proof of concept demonstration, we deploy the proposed method on a nano-drone named Crazyflie with a front camera to perform multi-goal navigation experiments.

We study provable multi-agent reinforcement learning (MARL) in the general framework of partially observable stochastic games (POSGs). To circumvent the known hardness results and the use of computationally intractable oracles, we advocate leveraging the potential \emph{information-sharing} among agents, a common practice in empirical MARL, and a standard model for multi-agent control systems with communications. We first establish several computation complexity results to justify the necessity of information-sharing, as well as the observability assumption that has enabled quasi-efficient single-agent RL with partial observations, for computational efficiency in solving POSGs. We then propose to further \emph{approximate} the shared common information to construct an {approximate model} of the POSG, in which planning an approximate equilibrium (in terms of solving the original POSG) can be quasi-efficient, i.e., of quasi-polynomial-time, under the aforementioned assumptions. Furthermore, we develop a partially observable MARL algorithm that is both statistically and computationally quasi-efficient. We hope our study may open up the possibilities of leveraging and even designing different \emph{information structures}, for developing both sample- and computation-efficient partially observable MARL.

This article investigates the use of Deep Q-Networks (DQNs) to optimize decision-making for photovoltaic (PV) systems installations in the agriculture sector. The study develops a DQN framework to assist agricultural investors in making informed decisions considering factors such as installation budget, government incentives, energy requirements, system cost, and long-term benefits. By implementing a reward mechanism, the DQN learns to make data-driven decisions on PV integration. The analysis provides a comprehensive understanding of how DQNs can support investors in making decisions about PV installations in agriculture. This research has significant implications for promoting sustainable and efficient farming practices while also paving the way for future advancements in this field. By leveraging DQNs, agricultural investors can make optimized decisions that improve energy efficiency, reduce environmental impact, and enhance profitability. This study contributes to the advancement of PV integration in agriculture and encourages further innovation in this promising area.

This paper proposes a novel framework for identifying an agent's risk aversion using interactive questioning. Our study is conducted in two scenarios: a one-period case and an infinite horizon case. In the one-period case, we assume that the agent's risk aversion is characterized by a cost function of the state and a distortion risk measure. In the infinite horizon case, we model risk aversion with an additional component, a discount factor. Assuming the access to a finite set of candidates containing the agent's true risk aversion, we show that asking the agent to demonstrate her optimal policies in various environment, which may depend on their previous answers, is an effective means of identifying the agent's risk aversion. Specifically, we prove that the agent's risk aversion can be identified as the number of questions tends to infinity, and the questions are randomly designed. We also develop an algorithm for designing optimal questions and provide empirical evidence that our method learns risk aversion significantly faster than randomly designed questions in simulations. Our framework has important applications in robo-advising and provides a new approach for identifying an agent's risk preferences.

The field of robotic Flexible Endoscopes (FEs) has progressed significantly, offering a promising solution to reduce patient discomfort. However, the limited autonomy of most robotic FEs results in non-intuitive and challenging manoeuvres, constraining their application in clinical settings. While previous studies have employed lumen tracking for autonomous navigation, they fail to adapt to the presence of obstructions and sharp turns when the endoscope faces the colon wall. In this work, we propose a Deep Reinforcement Learning (DRL)-based navigation strategy that eliminates the need for lumen tracking. However, the use of DRL methods poses safety risks as they do not account for potential hazards associated with the actions taken. To ensure safety, we exploit a Constrained Reinforcement Learning (CRL) method to restrict the policy in a predefined safety regime. Moreover, we present a model selection strategy that utilises Formal Verification (FV) to choose a policy that is entirely safe before deployment. We validate our approach in a virtual colonoscopy environment and report that out of the 300 trained policies, we could identify three policies that are entirely safe. Our work demonstrates that CRL, combined with model selection through FV, can improve the robustness and safety of robotic behaviour in surgical applications.

As Exascale computing becomes a reality, the energy needs of compute nodes in cloud data centers will continue to grow. A common approach to reducing this energy demand is to limit the power consumption of hardware components when workloads are experiencing bottlenecks elsewhere in the system. However, designing a resource controller capable of detecting and limiting power consumption on-the-fly is a complex issue and can also adversely impact application performance. In this paper, we explore the use of Reinforcement Learning (RL) to design a power capping policy on cloud compute nodes using observations on current power consumption and instantaneous application performance (heartbeats). By leveraging the Argo Node Resource Management (NRM) software stack in conjunction with the Intel Running Average Power Limit (RAPL) hardware control mechanism, we design an agent to control the maximum supplied power to processors without compromising on application performance. Employing a Proximal Policy Optimization (PPO) agent to learn an optimal policy on a mathematical model of the compute nodes, we demonstrate and evaluate using the STREAM benchmark how a trained agent running on actual hardware can take actions by balancing power consumption and application performance.

Deep reinforcement learning algorithms are usually impeded by sampling inefficiency, heavily depending on multiple interactions with the environment to acquire accurate decision-making capabilities. In contrast, humans rely on their hippocampus to retrieve relevant information from past experiences of relevant tasks, which guides their decision-making when learning a new task, rather than exclusively depending on environmental interactions. Nevertheless, designing a hippocampus-like module for an agent to incorporate past experiences into established reinforcement learning algorithms presents two challenges. The first challenge involves selecting the most relevant past experiences for the current task, and the second challenge is integrating such experiences into the decision network. To address these challenges, we propose a novel method that utilizes a retrieval network based on task-conditioned hypernetwork, which adapts the retrieval network's parameters depending on the task. At the same time, a dynamic modification mechanism enhances the collaborative efforts between the retrieval and decision networks. We evaluate the proposed method on the MiniGrid environment.The experimental results demonstrate that our proposed method significantly outperforms strong baselines.

Recent work on deep reinforcement learning (DRL) has pointed out that algorithmic information about good policies can be extracted from offline data which lack explicit information about executed actions. For example, videos of humans or robots may convey a lot of implicit information about rewarding action sequences, but a DRL machine that wants to profit from watching such videos must first learn by itself to identify and recognize relevant states/actions/rewards. Without relying on ground-truth annotations, our new method called Deep State Identifier learns to predict returns from episodes encoded as videos. Then it uses a kind of mask-based sensitivity analysis to extract/identify important critical states. Extensive experiments showcase our method's potential for understanding and improving agent behavior. The source code and the generated datasets are available at https://github.com/AI-Initiative-KAUST/VideoRLCS.

Active Inference is a recent framework for modeling planning under uncertainty. Empirical and theoretical work have now begun to evaluate the strengths and weaknesses of this approach and how it might be improved. A recent extension - the sophisticated inference (SI) algorithm - improves performance on multi-step planning problems through recursive decision tree search. However, little work to date has been done to compare SI to other established planning algorithms. SI was also developed with a focus on inference as opposed to learning. The present paper has two aims. First, we compare performance of SI to Bayesian reinforcement learning (RL) schemes designed to solve similar problems. Second, we present an extension of SI - sophisticated learning (SL) - that more fully incorporates active learning during planning. SL maintains beliefs about how model parameters would change under the future observations expected under each policy. This allows a form of counterfactual retrospective inference in which the agent considers what could be learned from current or past observations given different future observations. To accomplish these aims, we make use of a novel, biologically inspired environment designed to highlight the problem structure for which SL offers a unique solution. Here, an agent must continually search for available (but changing) resources in the presence of competing affordances for information gain. Our simulations show that SL outperforms all other algorithms in this context - most notably, Bayes-adaptive RL and upper confidence bound algorithms, which aim to solve multi-step planning problems using similar principles (i.e., directed exploration and counterfactual reasoning). These results provide added support for the utility of Active Inference in solving this class of biologically-relevant problems and offer added tools for testing hypotheses about human cognition.