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.

Research on deep reinforcement learning (DRL) based production scheduling (PS) has gained a lot of attention in recent years, primarily due to the high demand for optimizing scheduling problems in diverse industry settings. Numerous studies are carried out and published as stand-alone experiments that often vary only slightly with respect to problem setups and solution approaches. The programmatic core of these experiments is typically very similar. Despite this fact, no standardized and resilient framework for experimentation on PS problems with DRL algorithms could be established so far. In this paper, we introduce schlably, a Python-based framework that provides researchers a comprehensive toolset to facilitate the development of PS solution strategies based on DRL. schlably eliminates the redundant overhead work that the creation of a sturdy and flexible backbone requires and increases the comparability and reusability of conducted research work.

In representative democracies, the election of new representatives in regular election cycles is meant to prevent corruption and other misbehavior by elected officials and to keep them accountable in service of the ``will of the people." This democratic ideal can be undermined when candidates are dishonest when campaigning for election over these multiple cycles or rounds of voting. Much of the work on COMSOC to date has investigated strategic actions in only a single round. We introduce a novel formal model of \emph{pandering}, or strategic preference reporting by candidates seeking to be elected, and examine the resilience of two democratic voting systems to pandering within a single round and across multiple rounds. The two voting systems we compare are Representative Democracy (RD) and Flexible Representative Democracy (FRD). For each voting system, our analysis centers on the types of strategies candidates employ and how voters update their views of candidates based on how the candidates have pandered in the past. We provide theoretical results on the complexity of pandering in our setting for a single cycle, formulate our problem for multiple cycles as a Markov Decision Process, and use reinforcement learning to study the effects of pandering by both single candidates and groups of candidates across a number of rounds.