In this paper, we introduce a regularized mean-field game and study learning of this game under an infinite-horizon discounted reward function. Regularization is introduced by adding a strongly concave regularization function to the one-stage reward function in the classical mean-field game model. We establish a value iteration based learning algorithm to this regularized mean-field game using fitted Q-learning. The regularization term in general makes reinforcement learning algorithm more robust to the system components. Moreover, it enables us to establish error analysis of the learning algorithm without imposing restrictive convexity assumptions on the system components, which are needed in the absence of a regularization term.

Exploration is critical for deep reinforcement learning in complex environments with high-dimensional observations and sparse rewards. To address this problem, recent approaches proposed to leverage intrinsic rewards to improve exploration, such as novelty-based exploration and prediction-based exploration. However, many intrinsic reward modules require sophisticated structures and representation learning, resulting in prohibitive computational complexity and unstable performance. In this paper, we propose Rewarding Episodic Visitation Discrepancy (REVD), a computation-efficient and quantified exploration method. More specifically, REVD provides intrinsic rewards by evaluating the R\'enyi divergence-based visitation discrepancy between episodes. To make efficient divergence estimation, a k-nearest neighbor estimator is utilized with a randomly-initialized state encoder. Finally, the REVD is tested on Atari games and PyBullet Robotics Environments. Extensive experiments demonstrate that REVD can significantly improves the sample efficiency of reinforcement learning algorithms and outperforms the benchmarking methods.

In this work, we focus on the problem of safe policy transfer in reinforcement learning: we seek to leverage existing policies when learning a new task with specified constraints. This problem is important for safety-critical applications where interactions are costly and unconstrained policies can lead to undesirable or dangerous outcomes, e.g., with physical robots that interact with humans. We propose a Constrained Markov Decision Process (CMDP) formulation that simultaneously enables the transfer of policies and adherence to safety constraints. Our formulation cleanly separates task goals from safety considerations and permits the specification of a wide variety of constraints. Our approach relies on a novel extension of generalized policy improvement to constrained settings via a Lagrangian formulation. We devise a dual optimization algorithm that estimates the optimal dual variable of a target task, thus enabling safe transfer of policies derived from successor features learned on source tasks. Our experiments in simulated domains show that our approach is effective; it visits unsafe states less frequently and outperforms alternative state-of-the-art methods when taking safety constraints into account.

The exponential growth in demand for digital services drives massive datacenter energy consumption and negative environmental impacts. Promoting sustainable solutions to pressing energy and digital infrastructure challenges is crucial. Several hyperscale cloud providers have announced plans to power their datacenters using renewable energy. However, integrating renewables to power the datacenters is challenging because the power generation is intermittent, necessitating approaches to tackle power supply variability. Hand engineering domain-specific heuristics-based schedulers to meet specific objective functions in such complex dynamic green datacenter environments is time-consuming, expensive, and requires extensive tuning by domain experts. The green datacenters need smart systems and system software to employ multiple renewable energy sources (wind and solar) by intelligently adapting computing to renewable energy generation. We present RARE (Renewable energy Aware REsource management), a Deep Reinforcement Learning (DRL) job scheduler that automatically learns effective job scheduling policies while continually adapting to datacenters' complex dynamic environment. The resulting DRL scheduler performs better than heuristic scheduling policies with different workloads and adapts to the intermittent power supply from renewables. We demonstrate DRL scheduler system design parameters that, when tuned correctly, produce better performance. Finally, we demonstrate that the DRL scheduler can learn from and improve upon existing heuristic policies using Offline Learning.

Abstract: We present a novel method to address the problem of multi-vehicle conflict resolution in highly constrained spaces. An optimal control problem is formulated to incorporate nonlinear, non-holonomic vehicle dynamics and exact collision avoidance constraints. A solution to the problem can be obtained by first learning configuration strategies with reinforcement learning (RL) in a simplified discrete environment, and then using these strategies to shape the constraint space of the original problem. Simulation results show that our method can explore efficient actions to resolve conflicts in confined space and generate dexterous maneuvers that are both collision-free and kinematically feasible. Keywords: Trajectory and Path Planning, Multi-vehicle systems, Autonomous Vehicles, Reinforcement learning control, Control problems under conflict 1. INTRODUCTION When conflicts arise in highly constrained spaces such as crowded parking lots, both the optimal control and the RL approaches often fail due to the following reasons: Current autonomous vehicles (AVs) operate reasonably well in environments where traffic rules are well-defined, (i) The vehicles need to plan for combinatorial actions in the surrounding agents are rational, and their actions can order to create spaces for each other to pass through; be easily predicted.

In contrast, the setting of fully observable (FO) control has featured the success of many powerful reinforcement learning (RL) algorithms (e.g., [8, 9, 10, 11]). Unfortunately, full observability only holds for a small portion of realistic robotics problems. Figure 1: To reach the In this work, we attempt to leverage good fully observable policies (state correct goal object, a experts) available only during offline training to help train PO policies state expert takes the that can execute online. We rely on the setting of offline training and red path directly, while online execution, a successful RL framework where an agent can use a partially observable "privileged" information such as the state [12, 13, 14, 15] or the belief agent must first take the about the state [6] during offline training, e.g., from simulators, to efficiently green path to identify learn PO policies that are later can be deployed without the access the correct goal object, to the privileged information anymore. In this work, the privileged information then take the red path. is not just the state itself but also the state expert. Our setting can be illustrated in a navigation task (Figure 1), which requires an agent to navigate to an unknown goal object on the right, identifiable by an object on the left side. While the optimal behavior under partial observability is to first navigate leftwards to identify the goal object, the state expert is able to move to the goal object directly. Despite being sup-optimal from the PO perspective, the state expert can provide experience during training leading to the goal object, which is potentially useful for both exploration and as a part of the policy needed in the PO case after the goal object is identified.

The energy sector is facing rapid changes in the transition towards clean renewable sources. However, the growing share of volatile, fluctuating renewable generation such as wind or solar energy has already led to an increase in power grid congestion and network security concerns. Grid operators mitigate these by modifying either generation or demand (redispatching, curtailment, flexible loads). Unfortunately, redispatching of fossil generators leads to excessive grid operation costs and higher emissions, which is in direct opposition to the decarbonization of the energy sector. In this paper, we propose an AlphaZero-based grid topology optimization agent as a non-costly, carbon-free congestion management alternative. Our experimental evaluation confirms the potential of topology optimization for power grid operation, achieves a reduction of the average amount of required redispatching by 60%, and shows the interoperability with traditional congestion management methods. Our approach also ranked 1st in the WCCI 2022 Learning to Run a Power Network (L2RPN) competition. Based on our findings, we identify and discuss open research problems as well as technical challenges for a productive system on a real power grid.

Real-world reinforcement learning tasks often involve some form of partial observability where the observations only give a partial or noisy view of the true state of the world. Such tasks typically require some form of memory, where the agent has access to multiple past observations, in order to perform well. One popular way to incorporate memory is by using a recurrent neural network to access the agent's history. However, recurrent neural networks in reinforcement learning are often fragile and difficult to train, susceptible to catastrophic forgetting and sometimes fail completely as a result. In this work, we propose Deep Transformer Q-Networks (DTQN), a novel architecture utilizing transformers and self-attention to encode an agent's history. DTQN is designed modularly, and we compare results against several modifications to our base model. Our experiments demonstrate the transformer can solve partially observable tasks faster and more stably than previous recurrent approaches.

Reinforcement learning, another type of machine learning, is based on algorithms that learn through trial and error which actions to take to achieve a …

Machine learning frameworks such as Genetic Programming (GP) and Reinforcement Learning (RL) are gaining popularity in flow control. This work presents a comparative analysis of the two, bench-marking some of their most representative algorithms against global optimization techniques such as Bayesian Optimization (BO) and Lipschitz global optimization (LIPO). First, we review the general framework of the model-free control problem, bringing together all methods as black-box optimization problems. Then, we test the control algorithms on three test cases. These are (1) the stabilization of a nonlinear dynamical system featuring frequency cross-talk, (2) the wave cancellation from a Burgers' flow and (3) the drag reduction in a cylinder wake flow. We present a comprehensive comparison to illustrate their differences in exploration versus exploitation and their balance between `model capacity' in the control law definition versus `required complexity'. We believe that such a comparison paves the way toward the hybridization of the various methods, and we offer some perspective on their future development in the literature on flow control problems.