This letter presents a novel approach in the field of Active Fault Detection (AFD), by explicitly separating the task into two parts: Passive Fault Detection (PFD) and control input design. This formulation is very general, and most existing AFD literature can be viewed through this lens. By recognizing this separation, PFD methods can be leveraged to provide components that make efficient use of the available information, while the control input is designed in order to optimize the gathering of information. The core contribution of this work is FIERL, a general simulation-based approach for the design of such control strategies, using Constrained Reinforcement Learning (CRL) to optimize the performance of arbitrary passive detectors. The control policy is learned without the need of knowing the passive detector inner workings, making FIERL broadly applicable. However, it is especially useful when paired with the design of an efficient passive component. Unlike most AFD approaches, FIERL can handle fairly complex scenarios such as continuous sets of fault modes. The effectiveness of FIERL is tested on a benchmark problem for actuator fault diagnosis, where FIERL is shown to be fairly robust, being able to generalize to fault dynamics not seen in training.

We present a multi-agent reinforcement learning approach to solve a pursuit-evasion game between two players with car-like dynamics and sensing limitations. We develop a curriculum for an existing multi-agent deterministic policy gradient algorithm to simultaneously obtain strategies for both players, and deploy the learned strategies on real robots moving as fast as 2 m/s in indoor environments. Through experiments we show that the learned strategies improve over existing baselines by up to 30% in terms of capture rate for the pursuer. The learned evader model has up to 5% better escape rate over the baselines even against our competitive pursuer model. We also present experiment results which show how the pursuit-evasion game and its results evolve as the player dynamics and sensor constraints are varied. Finally, we deploy learned policies on physical robots for a game between the F1TENTH and JetRacer platforms and show that the learned strategies can be executed on real-robots. Our code and supplementary material including videos from experiments are available at https: //gonultasbu.github.io/pursuit-evasion/.

Offline optimization is an emerging problem in many experimental engineering domains including protein, drug or aircraft design, where online experimentation to collect evaluation data is too expensive or dangerous. To avoid that, one has to optimize an unknown function given only its offline evaluation at a fixed set of inputs. A naive solution to this problem is to learn a surrogate model of the unknown function and optimize this surrogate instead. However, such a naive optimizer is prone to erroneous overestimation of the surrogate (possibly due to over-fitting on a biased sample of function evaluation) on inputs outside the offline dataset. Prior approaches addressing this challenge have primarily focused on learning robust surrogate models. However, their search strategies are derived from the surrogate model rather than the actual offline data. To fill this important gap, we introduce a new learning-to-search perspective for offline optimization by reformulating it as an offline reinforcement learning problem. Our proposed policy-guided gradient search approach explicitly learns the best policy for a given surrogate model created from the offline data. Our empirical results on multiple benchmarks demonstrate that the learned optimization policy can be combined with existing offline surrogates to significantly improve the optimization performance.

Investment portfolios, central to finance, balance potential returns and risks. This paper introduces a hybrid approach combining Markowitz's portfolio theory with reinforcement learning, utilizing knowledge distillation for training agents. In particular, our proposed method, called KDD (Knowledge Distillation DDPG), consist of two training stages: supervised and reinforcement learning stages. The trained agents optimize portfolio assembly. A comparative analysis against standard financial models and AI frameworks, using metrics like returns, the Sharpe ratio, and nine evaluation indices, reveals our model's superiority. It notably achieves the highest yield and Sharpe ratio of 2.03, ensuring top profitability with the lowest risk in comparable return scenarios.

In the smart grid, the prosumers can sell unused electricity back to the power grid, assuming the prosumers own renewable energy sources and storage units. The maximizing of their profits under a dynamic electricity market is a problem that requires intelligent planning. To address this, we propose a framework based on Proximal Policy Optimization (PPO) using recurrent rewards. By using the information about the rewards modeled effectively with PPO to maximize our objective, we were able to get over 30\% improvement over the other naive algorithms in accumulating total profits. This shows promise in getting reinforcement learning algorithms to perform tasks required to plan their actions in complex domains like financial markets. We also introduce a novel method for embedding longs based on soliton waves that outperformed normal embedding in our use case with random floating point data augmentation.

Recent work in reinforcement learning has leveraged symmetries in the model to improve sample efficiency in training a policy. A commonly used simplifying assumption is that the dynamics and reward both exhibit the same symmetry. However, in many real-world environments, the dynamical model exhibits symmetry independent of the reward model: the reward may not satisfy the same symmetries as the dynamics. In this paper, we investigate scenarios where only the dynamics are assumed to exhibit symmetry, extending the scope of problems in reinforcement learning and learning in control theory where symmetry techniques can be applied. We use Cartan's moving frame method to introduce a technique for learning dynamics which, by construction, exhibit specified symmetries. We demonstrate through numerical experiments that the proposed method learns a more accurate dynamical model.

To overcome the sim-to-real gap in reinforcement learning (RL), learned policies must maintain robustness against environmental uncertainties. While robust RL has been widely studied in single-agent regimes, in multi-agent environments, the problem remains understudied -- despite the fact that the problems posed by environmental uncertainties are often exacerbated by strategic interactions. This work focuses on learning in distributionally robust Markov games (RMGs), a robust variant of standard Markov games, wherein each agent aims to learn a policy that maximizes its own worst-case performance when the deployed environment deviates within its own prescribed uncertainty set. This results in a set of robust equilibrium strategies for all agents that align with classic notions of game-theoretic equilibria. Assuming a non-adaptive sampling mechanism from a generative model, we propose a sample-efficient model-based algorithm (DRNVI) with finite-sample complexity guarantees for learning robust variants of various notions of game-theoretic equilibria. We also establish an information-theoretic lower bound for solving RMGs, which confirms the near-optimal sample complexity of DRNVI with respect to problem-dependent factors such as the size of the state space, the target accuracy, and the horizon length.

The robust $\phi$-regularized Markov Decision Process (RRMDP) framework focuses on designing control policies that are robust against parameter uncertainties due to mismatches between the simulator (nominal) model and real-world settings. This work makes two important contributions. First, we propose a model-free algorithm called Robust $\phi$-regularized fitted Q-iteration (RPQ) for learning an $\epsilon$-optimal robust policy that uses only the historical data collected by rolling out a behavior policy (with robust exploratory requirement) on the nominal model. To the best of our knowledge, we provide the first unified analysis for a class of $\phi$-divergences achieving robust optimal policies in high-dimensional systems with general function approximation. Second, we introduce the hybrid robust $\phi$-regularized reinforcement learning framework to learn an optimal robust policy using both historical data and online sampling. Towards this framework, we propose a model-free algorithm called Hybrid robust Total-variation-regularized Q-iteration (HyTQ: pronounced height-Q). To the best of our knowledge, we provide the first improved out-of-data-distribution assumption in large-scale problems with general function approximation under the hybrid robust $\phi$-regularized reinforcement learning framework. Finally, we provide theoretical guarantees on the performance of the learned policies of our algorithms on systems with arbitrary large state space.

We uncover a surprising phenomenon in deep reinforcement learning: training a diverse ensemble of data-sharing agents - a well-established exploration strategy - can significantly impair the performance of the individual ensemble members when compared to standard single-agent training. Through careful analysis, we attribute the degradation in performance to the low proportion of self-generated data in the shared training data for each ensemble member, as well as the inefficiency of the individual ensemble members to learn from such highly off-policy data. We thus name this phenomenon the curse of diversity. We find that several intuitive solutions - such as a larger replay buffer or a smaller ensemble size - either fail to consistently mitigate the performance loss or undermine the advantages of ensembling. Finally, we demonstrate the potential of representation learning to counteract the curse of diversity with a novel method named Cross-Ensemble Representation Learning (CERL) in both discrete and continuous control domains. Our work offers valuable insights into an unexpected pitfall in ensemble-based exploration and raises important caveats for future applications of similar approaches. The potential benefits of a diverse ensemble are twofold. At training time, it enables concurrent exploration with multiple distinct policies without the need for additional samples. At test time, the learned policies can be aggregated into a robust ensemble policy, via aggregation methods such as majority voting (Osband et al., 2016) or averaging (Januszewski et al., 2021). Despite the generally positive perception of ensemble-based exploration, we argue that this approach has a potentially negative aspect that has been long overlooked. As shown in Figure 1, for each member in a data-sharing ensemble, only a small proportion of its training data comes from its own interaction with the environment. The majority of its training data is generated by other members of the ensemble, whose policies might be distinct from its own policy. This type of off-policy learning has been shown to be highly challenging in previous work (Ostrovski et al., 2021). We thus hypothesize that similar learning difficulties can also occur in ensemble-based exploration. We verify our hypothesis in the Arcade Learning Environment (Bellemare et al., 2012) with the Bootstrapped DQN (Osband et al., 2016) algorithm and the Gym MuJoCo benchmark (Towers et al., 2023) with an ensemble SAC (Haarnoja et al., 2018a) algorithm. We show that, in many environments, the individual members of a data-sharing ensemble significantly underperform their single-agent counterparts. Moreover, while aggregating the policies of all ensemble members via voting or averaging sometimes compensates for the degradation in individual members' performance, it is not always the case.

The training, testing, and deployment, of autonomous vehicles requires realistic and efficient simulators. Moreover, because of the high variability between different problems presented in different autonomous systems, these simulators need to be easy to use, and easy to modify. To address these problems we introduce TorchDriveSim and its benchmark extension TorchDriveEnv. TorchDriveEnv is a lightweight reinforcement learning benchmark programmed entirely in Python, which can be modified to test a number of different factors in learned vehicle behavior, including the effect of varying kinematic models, agent types, and traffic control patterns. Most importantly unlike many replay based simulation approaches, TorchDriveEnv is fully integrated with a state of the art behavioral simulation API. This allows users to train and evaluate driving models alongside data driven Non-Playable Characters (NPC) whose initializations and driving behavior are reactive, realistic, and diverse. We illustrate the efficiency and simplicity of TorchDriveEnv by evaluating common reinforcement learning baselines in both training and validation environments. Our experiments show that TorchDriveEnv is easy to use, but difficult to solve.