In this paper, we address the problem of designing incentive mechanisms by a virtual service provider (VSP) to hire sensing IoT devices to sell their sensing data to help creating and rendering the digital copy of the physical world in the Metaverse. Due to the limited bandwidth, we propose to use semantic extraction algorithms to reduce the delivered data by the sensing IoT devices. Nevertheless, mechanisms to hire sensing IoT devices to share their data with the VSP and then deliver the constructed digital twin to the Metaverse users are vulnerable to adverse selection problem. The adverse selection problem, which is caused by information asymmetry between the system entities, becomes harder to solve when the private information of the different entities are multi-dimensional. We propose a novel iterative contract design and use a new variant of multi-agent reinforcement learning (MARL) to solve the modelled multi-dimensional contract problem. To demonstrate the effectiveness of our algorithm, we conduct extensive simulations and measure several key performance metrics of the contract for the Metaverse. Our results show that our designed iterative contract is able to incentivize the participants to interact truthfully, which maximizes the profit of the VSP with minimal individual rationality (IR) and incentive compatibility (IC) violation rates. Furthermore, the proposed learning-based iterative contract framework has limited access to the private information of the participants, which is to the best of our knowledge, the first of its kind in addressing the problem of adverse selection in incentive mechanisms.

Multi-rotor UAVs suffer from a restricted range and flight duration due to limited battery capacity. Autonomous landing on a 2D moving platform offers the possibility to replenish batteries and offload data, thus increasing the utility of the vehicle. Classical approaches rely on accurate, complex and difficult-to-derive models of the vehicle and the environment. Reinforcement learning (RL) provides an attractive alternative due to its ability to learn a suitable control policy exclusively from data during a training procedure. However, current methods require several hours to train, have limited success rates and depend on hyperparameters that need to be tuned by trial-and-error. We address all these issues in this work. First, we decompose the landing procedure into a sequence of simpler, but similar learning tasks. This is enabled by applying two instances of the same RL based controller trained for 1D motion for controlling the multi-rotor's movement in both the longitudinal and the lateral direction. Second, we introduce a powerful state space discretization technique that is based on i) kinematic modeling of the moving platform to derive information about the state space topology and ii) structuring the training as a sequential curriculum using transfer learning. Third, we leverage the kinematics model of the moving platform to also derive interpretable hyperparameters for the training process that ensure sufficient maneuverability of the multi-rotor vehicle. The training is performed using the tabular RL method Double Q-Learning. Through extensive simulations we show that the presented method significantly increases the rate of successful landings, while requiring less training time compared to other deep RL approaches. Finally, we deploy and demonstrate our algorithm on real hardware. For all evaluation scenarios we provide statistics on the agent's performance.

Deep reinforcement learning (DRL) has been widely applied in autonomous exploration and mapping tasks, but often struggles with the challenges of sampling efficiency, poor adaptability to unknown map sizes, and slow simulation speed. To speed up convergence, we combine curriculum learning (CL) with DRL, and first propose a Cumulative Curriculum Reinforcement Learning (CCRL) training framework to alleviate the issue of catastrophic forgetting faced by general CL. Besides, we present a novel state representation, which considers a local egocentric map and a global exploration map resized to the fixed dimension, so as to flexibly adapt to environments with various sizes and shapes. Additionally, for facilitating the fast training of DRL models, we develop a lightweight grid-based simulator, which can substantially accelerate simulation compared to popular robot simulation platforms such as Gazebo. Based on the customized simulator, comprehensive experiments have been conducted, and the results show that the CCRL framework not only mitigates the catastrophic forgetting problem, but also improves the sample efficiency and generalization of DRL models, compared to general CL as well as without a curriculum. Our code is available at https://github.com/BeamanLi/CCRL_Exploration.

The needs describe the necessities for a system to survive and evolve, which arouses an agent to action toward a goal, giving purpose and direction to behavior. Based on Maslow hierarchy of needs, an agent needs to satisfy a certain amount of needs at the current level as a condition to arise at the next stage -- upgrade and evolution. Especially, Deep Reinforcement Learning (DAL) can help AI agents (like robots) organize and optimize their behaviors and strategies to develop diverse Strategies based on their current state and needs (expected utilities or rewards). This paper introduces the new hierarchical needs-driven Learning systems based on DAL and investigates the implementation in the single-robot with a novel approach termed Bayesian Soft Actor-Critic (BSAC). Then, we extend this topic to the Multi-Agent systems (MAS), discussing the potential research fields and directions.

This paper presents an equivariant reinforcement learning framework for quadrotor unmanned aerial vehicles. Successful training of reinforcement learning often requires numerous interactions with the environments, which hinders its applicability especially when the available computational resources are limited, or when there is no reliable simulation model. We identified an equivariance property of the quadrotor dynamics such that the dimension of the state required in the training is reduced by one, thereby improving the sampling efficiency of reinforcement learning substantially. This is illustrated by numerical examples with popular reinforcement learning techniques of TD3 and SAC.

In this paper, based on the spirit of Fitted Q-Iteration (FQI), we propose a Gauss-Newton Temporal Difference (GNTD) method to solve the Q-value estimation problem with function approximation. In each iteration, unlike the original FQI that solves a nonlinear least square subproblem to fit the Q-iteration, the GNTD method can be viewed as an \emph{inexact} FQI that takes only one Gauss-Newton step to optimize this subproblem, which is much cheaper in computation. Compared to the popular Temporal Difference (TD) learning, which can be viewed as taking a single gradient descent step to FQI's subproblem per iteration, the Gauss-Newton step of GNTD better retains the structure of FQI and hence leads to better convergence. In our work, we derive the finite-sample non-asymptotic convergence of GNTD under linear, neural network, and general smooth function approximations. In particular, recent works on neural TD only guarantee a suboptimal $\mathcal{\mathcal{O}}(\epsilon^{-4})$ sample complexity, while GNTD obtains an improved complexity of $\tilde{\mathcal{O}}(\epsilon^{-2})$. Finally, we validate our method via extensive experiments in both online and offline RL problems. Our method exhibits both higher rewards and faster convergence than TD-type methods, including DQN.

In many real-world reinforcement learning (RL) tasks, limited computing resources make it challenging to apply fully adaptive algorithms that continually update the exploration policy. As a surrogate, it is more cost-effective to collect data in large batches using the current policy and make changes to the policy after the entire batch is completed. For example, in a recommendation system [Afsar et al., 2021], it is easier to gather new data quickly, but deploying a new policy takes longer as it requires significant computing and human resources. Therefore, it's not feasible to switch policies based on real-time data, as typical RL algorithms would require. A practical solution is to run several experiments in parallel and make decisions on policy updates only after the entire batch has been completed. Similar limitations occur in other RL based applications such as healthcare [Yu et al., 2021], robotics [Kober et al., 2013], and new material design [Zhou et al., 2019], where the agent must minimize the number of policy updates while still learning an effective policy using a similar number of trajectories as fully-adaptive methods. On the theoretical side, Bai et al. [2019] brought up the definition of switching cost, which measures the number of policy updates.

We study a heterogeneous agent macroeconomic model with an infinite number of households and firms competing in a labor market. Each household earns income and engages in consumption at each time step while aiming to maximize a concave utility subject to the underlying market conditions. The households aim to find the optimal saving strategy that maximizes their discounted cumulative utility given the market condition, while the firms determine the market conditions through maximizing corporate profit based on the household population behavior. The model captures a wide range of applications in macroeconomic studies, and we propose a data-driven reinforcement learning framework that finds the regularized competitive equilibrium of the model. The proposed algorithm enjoys theoretical guarantees in converging to the equilibrium of the market at a sub-linear rate.

A fundamental question in reinforcement learning theory is: suppose the optimal value functions are linear in given features, can we learn them efficiently? This problem's counterpart in supervised learning, linear regression, can be solved both statistically and computationally efficiently. Therefore, it was quite surprising when a recent work \cite{kane2022computational} showed a computational-statistical gap for linear reinforcement learning: even though there are polynomial sample-complexity algorithms, unless NP = RP, there are no polynomial time algorithms for this setting. In this work, we build on their result to show a computational lower bound, which is exponential in feature dimension and horizon, for linear reinforcement learning under the Randomized Exponential Time Hypothesis. To prove this we build a round-based game where in each round the learner is searching for an unknown vector in a unit hypercube. The rewards in this game are chosen such that if the learner achieves large reward, then the learner's actions can be used to simulate solving a variant of 3-SAT, where (a) each variable shows up in a bounded number of clauses (b) if an instance has no solutions then it also has no solutions that satisfy more than (1-$\epsilon$)-fraction of clauses. We use standard reductions to show this 3-SAT variant is approximately as hard as 3-SAT. Finally, we also show a lower bound optimized for horizon dependence that almost matches the best known upper bound of $\exp(\sqrt{H})$.

Internet-of-Things (IoT) devices are often used to transmit physical sensor data over digital wireless channels. Traditional Physical Layer Security (PLS)-based cryptography approaches rely on accurate channel estimation and information exchange for key generation, which irrevocably ties key quality with digital channel estimation quality. Recently, we proposed a new concept called Graph Layer Security (GLS), where digital keys are derived from physical sensor readings. The sensor readings between legitimate users are correlated through a common background infrastructure environment (e.g., a common water distribution network or electric grid). The challenge for GLS has been how to achieve distributed key generation. This paper presents a Federated multi-agent Deep reinforcement learning-assisted Distributed Key generation scheme (FD2K), which fully exploits the common features of physical dynamics to establish secret key between legitimate users. We present for the first time initial experimental results of GLS with federated learning, achieving considerable security performance in terms of key agreement rate (KAR), and key randomness.