Federated learning (FL) has recently gained much attention due to its effectiveness in speeding up supervised learning tasks under communication and privacy constraints. However, whether similar speedups can be established for reinforcement learning remains much less understood theoretically. Towards this direction, we study a federated policy evaluation problem where agents communicate via a central aggregator to expedite the evaluation of a common policy. To capture typical communication constraints in FL, we consider finite capacity up-link channels that can drop packets based on a Bernoulli erasure model. Given this setting, we propose and analyze QFedTD - a quantized federated temporal difference learning algorithm with linear function approximation. Our main technical contribution is to provide a finite-sample analysis of QFedTD that (i) highlights the effect of quantization and erasures on the convergence rate; and (ii) establishes a linear speedup w.r.t. the number of agents under Markovian sampling. Notably, while different quantization mechanisms and packet drop models have been extensively studied in the federated learning, distributed optimization, and networked control systems literature, our work is the first to provide a non-asymptotic analysis of their effects in multi-agent and federated reinforcement learning.

Determining multi-robot motion policies for persistently monitoring a region with limited sensing, communication, and localization constraints in non-GPS environments is a challenging problem. To take the localization constraints into account, in this paper, we consider a heterogeneous robotic system consisting of two types of agents: anchor agents with accurate localization capability and auxiliary agents with low localization accuracy. To localize itself, the auxiliary agents must be within the communication range of an {anchor}, directly or indirectly. The robotic team's objective is to minimize environmental uncertainty through persistent monitoring. We propose a multi-agent deep reinforcement learning (MARL) based architecture with graph convolution called Graph Localized Proximal Policy Optimization (GALOPP), which incorporates the limited sensor field-of-view, communication, and localization constraints of the agents along with persistent monitoring objectives to determine motion policies for each agent. We evaluate the performance of GALOPP on open maps with obstacles having a different number of anchor and auxiliary agents. We further study (i) the effect of communication range, obstacle density, and sensing range on the performance and (ii) compare the performance of GALOPP with non-RL baselines, namely, greedy search, random search, and random search with communication constraint. For its generalization capability, we also evaluated GALOPP in two different environments -- 2-room and 4-room. The results show that GALOPP learns the policies and monitors the area well. As a proof-of-concept, we perform hardware experiments to demonstrate the performance of GALOPP.

We apply reinforcement learning (RL) to robotics tasks. One of the drawbacks of traditional RL algorithms has been their poor sample efficiency. One approach to improve the sample efficiency is model-based RL. In our model-based RL algorithm, we learn a model of the environment, essentially its transition dynamics and reward function, use it to generate imaginary trajectories and backpropagate through them to update the policy, exploiting the differentiability of the model. Intuitively, learning more accurate models should lead to better model-based RL performance. Recently, there has been growing interest in developing better deep neural network based dynamics models for physical systems, by utilizing the structure of the underlying physics. We focus on robotic systems undergoing rigid body motion without contacts. We compare two versions of our model-based RL algorithm, one which uses a standard deep neural network based dynamics model and the other which uses a much more accurate, physics-informed neural network based dynamics model. We show that, in model-based RL, model accuracy mainly matters in environments that are sensitive to initial conditions, where numerical errors accumulate fast. In these environments, the physics-informed version of our algorithm achieves significantly better average-return and sample efficiency. In environments that are not sensitive to initial conditions, both versions of our algorithm achieve similar average-return, while the physics-informed version achieves better sample efficiency. We also show that, in challenging environments, physics-informed model-based RL achieves better average-return than state-of-the-art model-free RL algorithms such as Soft Actor-Critic, as it computes the policy-gradient analytically, while the latter estimates it through sampling.

This paper studies a class of multi-agent reinforcement learning (MARL) problems where the reward that an agent receives depends on the states of other agents, but the next state only depends on the agent's own current state and action. We name it REC-MARL standing for REward-Coupled Multi-Agent Reinforcement Learning. REC-MARL has a range of important applications such as real-time access control and distributed power control in wireless networks. This paper presents a distributed policy gradient algorithm for REC-MARL. The proposed algorithm is distributed in two aspects: (i) the learned policy is a distributed policy that maps a local state of an agent to its local action and (ii) the learning/training is distributed, during which each agent updates its policy based on its own and neighbors' information. The learned algorithm achieves a stationary policy and its iterative complexity bounds depend on the dimension of local states and actions. The experimental results of our algorithm for the real-time access control and power control in wireless networks show that our policy significantly outperforms the state-of-the-art algorithms and well-known benchmarks.

In this work, we propose a novel inverse reinforcement learning (IRL) algorithm for constrained Markov decision process (CMDP) problems. In standard IRL problems, the inverse learner or agent seeks to recover the reward function of the MDP, given a set of trajectory demonstrations for the optimal policy. In this work, we seek to infer not only the reward functions of the CMDP, but also the constraints. Using the principle of maximum entropy, we show that the IRL with constraint recovery (IRL-CR) problem can be cast as a constrained non-convex optimization problem. We reduce it to an alternating constrained optimization problem whose sub-problems are convex. We use exponentiated gradient descent algorithm to solve it. Finally, we demonstrate the efficacy of our algorithm for the grid world environment.

Recent years have noticed an increasing interest among academia and industry towards analyzing the electrical consumption of residential buildings and employing smart home energy management systems (HEMS) to reduce household energy consumption and costs. HEMS has been developed to simulate the statistical and functional properties of actual smart grids. Access to publicly available datasets is a major challenge in this type of research. The potential of artificial HEMS applications will be further enhanced with the development of time series that represent different operating conditions of the synthetic systems. In this paper, we propose a novel variational auto-encoder-generative adversarial network (VAE-GAN) technique for generating time-series data on energy consumption in smart homes. We also explore how the generative model performs when combined with a Q-learning-based HEMS. We tested the online performance of Q-learning-based HEMS with real-world smart home data. To test the generated dataset, we measure the Kullback-Leibler (KL) divergence, maximum mean discrepancy (MMD), and the Wasserstein distance between the probability distributions of the real and synthetic data. Our experiments show that VAE-GAN-generated synthetic data closely matches the real data distribution. Finally, we show that the generated data allows for the training of a higher-performance Q-learning-based HEMS compared to datasets generated with baseline approaches.

Policy Optimization (PO) is one of the most popular methods in Reinforcement Learning (RL). Thus, theoretical guarantees for PO algorithms have become especially important to the RL community. In this paper, we study PO in adversarial MDPs with a challenge that arises in almost every real-world application -- \textit{delayed bandit feedback}. We give the first near-optimal regret bounds for PO in tabular MDPs, and may even surpass state-of-the-art (which uses less efficient methods). Our novel Delay-Adapted PO (DAPO) is easy to implement and to generalize, allowing us to extend our algorithm to: (i) infinite state space under the assumption of linear $Q$-function, proving the first regret bounds for delayed feedback with function approximation. (ii) deep RL, demonstrating its effectiveness in experiments on MuJoCo domains.

In an offline reinforcement learning setting, the safe policy improvement (SPI) problem aims to improve the performance of a behavior policy according to which sample data has been generated. State-of-the-art approaches to SPI require a high number of samples to provide practical probabilistic guarantees on the improved policy's performance. We present a novel approach to the SPI problem that provides the means to require less data for such guarantees. Specifically, to prove the correctness of these guarantees, we devise implicit transformations on the data set and the underlying environment model that serve as theoretical foundations to derive tighter improvement bounds for SPI. Our empirical evaluation, using the well-established SPI with baseline bootstrapping (SPIBB) algorithm, on standard benchmarks shows that our method indeed significantly reduces the sample complexity of the SPIBB algorithm.

Multicast communication technology is widely applied in wireless environments with a high device density. Traditional wireless network architectures have difficulty flexibly obtaining and maintaining global network state information and cannot quickly respond to network state changes, thus affecting the throughput, delay, and other QoS requirements of existing multicasting solutions. Therefore, this paper proposes a new multicast routing method based on multiagent deep reinforcement learning (MADRL-MR) in a software-defined wireless networking (SDWN) environment. First, SDWN technology is adopted to flexibly configure the network and obtain network state information in the form of traffic matrices representing global network links information, such as link bandwidth, delay, and packet loss rate. Second, the multicast routing problem is divided into multiple subproblems, which are solved through multiagent cooperation. To enable each agent to accurately understand the current network state and the status of multicast tree construction, the state space of each agent is designed based on the traffic and multicast tree status matrices, and the set of AP nodes in the network is used as the action space. A novel single-hop action strategy is designed, along with a reward function based on the four states that may occur during tree construction: progress, invalid, loop, and termination. Finally, a decentralized training approach is combined with transfer learning to enable each agent to quickly adapt to dynamic network changes and accelerate convergence. Simulation experiments show that MADRL-MR outperforms existing algorithms in terms of throughput, delay, packet loss rate, etc., and can establish more intelligent multicast routes.

We investigate the problem of wireless routing in integrated access backhaul (IAB) networks consisting of fiber-connected and wireless base stations and multiple users. The physical constraints of these networks prevent the use of a central controller, and base stations have limited access to real-time network conditions. We aim to maximize packet arrival ratio while minimizing their latency, for this purpose, we formulate the problem as a multi-agent partially observed Markov decision process (POMDP). To solve this problem, we develop a Relational Advantage Actor Critic (Relational A2C) algorithm that uses Multi-Agent Reinforcement Learning (MARL) and information about similar destinations to derive a joint routing policy on a distributed basis. We present three training paradigms for this algorithm and demonstrate its ability to achieve near-centralized performance. Our results show that Relational A2C outperforms other reinforcement learning algorithms, leading to increased network efficiency and reduced selfish agent behavior. To the best of our knowledge, this work is the first to optimize routing strategy for IAB networks.