Classical reinforcement learning (RL) aims to optimize the expected cumulative reward. In this work, we consider the RL setting where the goal is to optimize the quantile of the cumulative reward. We parameterize the policy controlling actions by neural networks, and propose a novel policy gradient algorithm called Quantile-Based Policy Optimization (QPO) and its variant Quantile-Based Proximal Policy Optimization (QPPO) for solving deep RL problems with quantile objectives. QPO uses two coupled iterations running at different timescales for simultaneously updating quantiles and policy parameters, whereas QPPO is an off-policy version of QPO that allows multiple updates of parameters during one simulation episode, leading to improved algorithm efficiency. Our numerical results indicate that the proposed algorithms outperform the existing baseline algorithms under the quantile criterion.

Deep reinforcement learning (DRL) has emerged as a promising approach for developing more intelligent autonomous vehicles (AVs). A typical DRL application on AVs is to train a neural network-based driving policy. However, the black-box nature of neural networks can result in unpredictable decision failures, making such AVs unreliable. To this end, this work proposes a method to identify and protect unreliable decisions of a DRL driving policy. The basic idea is to estimate and constrain the policy's performance uncertainty, which quantifies potential performance drop due to insufficient training data or network fitting errors. By constraining the uncertainty, the DRL model's performance is always greater than that of a baseline policy. The uncertainty caused by insufficient data is estimated by the bootstrapped method. Then, the uncertainty caused by the network fitting error is estimated using an ensemble network. Finally, a baseline policy is added as the performance lower bound to avoid potential decision failures. The overall framework is called uncertainty-bound reinforcement learning (UBRL). The proposed UBRL is evaluated on DRL policies with different amounts of training data, taking an unprotected left-turn driving case as an example. The result shows that the UBRL method can identify potentially unreliable decisions of DRL policy. The UBRL guarantees to outperform baseline policy even when the DRL policy is not well-trained and has high uncertainty. Meanwhile, the performance of UBRL improves with more training data. Such a method is valuable for the DRL application on real-road driving and provides a metric to evaluate a DRL policy.

This paper presents a novel RL algorithm, S-REINFORCE, which is designed to generate interpretable policies for dynamic decision-making tasks. The proposed algorithm leverages two types of function approximators, namely Neural Network (NN) and Symbolic Regressor (SR), to produce numerical and symbolic policies, respectively. The NN component learns to generate a numerical probability distribution over the possible actions using a policy gradient, while the SR component captures the functional form that relates the associated states with the action probabilities. The SR-generated policy expressions are then utilized through importance sampling to improve the rewards received during the learning process. We have tested the proposed S-REINFORCE algorithm on various dynamic decision-making problems with low and high dimensional action spaces, and the results demonstrate its effectiveness and impact in achieving interpretable solutions. By leveraging the strengths of both NN and SR, S-REINFORCE produces policies that are not only well-performing but also easy to interpret, making it an ideal choice for real-world applications where transparency and causality are crucial.

Due to the highly dynamic changes in wireless network topologies, efficiently obtaining network status information and flexibly forwarding data to improve communication quality of service are important challenges. This article introduces an intelligent routing algorithm (DRL-PPONSA) based on proximal policy optimization deep reinforcement learning with network situational awareness under a software-defined wireless networking architecture. First, a specific data plane is designed for network topology construction and data forwarding. The control plane collects network traffic information, sends flow tables, and uses a GCN-GRU prediction mechanism to perceive future traffic change trends to achieve network situational awareness. Second, a DRL-based data forwarding mechanism is designed in the knowledge plane. The predicted network traffic matrix and topology information matrix are treated as the environment for DRL agents, while next-hop adjacent nodes are treated as executable actions. Accordingly, action selection strategies are designed for different network conditions to achieve more intelligent, flexible, and efficient routing control. The reward function is designed using network link information and various reward and penalty mechanisms. Additionally, importance sampling and gradient clipping techniques are employed during gradient updating to enhance convergence speed and stability. Experimental results show that DRL-PPONSA outperforms traditional routing methods in network throughput, delay, packet loss rate, and wireless node distance. Compared to value-function-based Dueling DQN routing, the convergence speed is significantly improved, and the convergence effect is more stable. Simultaneously, its consumption of hardware storage space is reduced, and efficient routing decisions can be made in real-time using the current network state information.

SARSA, a classical on-policy control algorithm for reinforcement learning, is known to chatter when combined with linear function approximation: SARSA does not diverge but oscillates in a bounded region. However, little is known about how fast SARSA converges to that region and how large the region is. In this paper, we make progress towards this open problem by showing the convergence rate of projected SARSA to a bounded region. Importantly, the region is much smaller than the region that we project into, provided that the magnitude of the reward is not too large. Existing works regarding the convergence of linear SARSA to a fixed point all require the Lipschitz constant of SARSA's policy improvement operator to be sufficiently small; our analysis instead applies to arbitrary Lipschitz constants and thus characterizes the behavior of linear SARSA for a new regime.

Diffusion models have demonstrated their powerful generative capability in many tasks, with great potential to serve as a paradigm for offline reinforcement learning. However, the quality of the diffusion model is limited by the insufficient diversity of training data, which hinders the performance of planning and the generalizability to new tasks. This paper introduces AdaptDiffuser, an evolutionary planning method with diffusion that can self-evolve to improve the diffusion model hence a better planner, not only for seen tasks but can also adapt to unseen tasks. AdaptDiffuser enables the generation of rich synthetic expert data for goal-conditioned tasks using guidance from reward gradients. It then selects high-quality data via a discriminator to finetune the diffusion model, which improves the generalization ability to unseen tasks. Empirical experiments on two benchmark environments and two carefully designed unseen tasks in KUKA industrial robot arm and Maze2D environments demonstrate the effectiveness of AdaptDiffuser. For example, AdaptDiffuser not only outperforms the previous art Diffuser by 20.8% on Maze2D and 7.5% on MuJoCo locomotion, but also adapts better to new tasks, e.g., KUKA pick-and-place, by 27.9% without requiring additional expert data. More visualization results and demo videos could be found on our project page.

Modern cellular networks are multi-cell and use universal frequency reuse to maximize spectral efficiency. This results in high inter-cell interference. This problem is growing as cellular networks become three-dimensional with the adoption of unmanned aerial vehicles (UAVs). This is because the strength and number of interference links rapidly increase due to the line-of-sight channels in UAV communications. Existing interference management solutions need each transmitter to know the channel information of interfering signals, rendering them impractical due to excessive signaling overhead. In this paper, we propose leveraging deep reinforcement learning for interference management to tackle this shortcoming. In particular, we show that interference can still be effectively mitigated even without knowing its channel information. We then discuss novel approaches to scale the algorithms with linear/sublinear complexity and decentralize them using multi-agent reinforcement learning. By harnessing interference, the proposed solutions enable the continued growth of civilian UAVs.

The increasing penetration of renewable generations, along with the deregulation and marketization of power industry, promotes the transformation of power market operation paradigms. The optimal bidding strategy and dispatching methodology under these new paradigms are prioritized concerns for both market participants and power system operators, with obstacles of uncertain characteristics, computational efficiency, as well as requirements of hyperopic decision-making. To tackle these problems, the Reinforcement Learning (RL), as an emerging machine learning technique with advantages compared with conventional optimization tools, is playing an increasingly significant role in both academia and industry. This paper presents a comprehensive review of RL applications in deregulated power market operation including bidding and dispatching strategy optimization, based on more than 150 carefully selected literatures. For each application, apart from a paradigmatic summary of generalized methodology, in-depth discussions of applicability and obstacles while deploying RL techniques are also provided. Finally, some RL techniques that have great potentiality to be deployed in bidding and dispatching problems are recommended and discussed.

Offline reinforcement learning--learning a policy from a batch of data--is known to be hard for general MDPs. These results motivate the need to look at specific classes of MDPs where offline reinforcement learning might be feasible. In this work, we explore a restricted class of MDPs to obtain guarantees for offline reinforcement learning. The key property, which we call Action Impact Regularity (AIR), is that actions primarily impact a part of the state (an endogenous component) and have limited impact on the remaining part of the state (an exogenous component). AIR is a strong assumption, but it nonetheless holds in a number of real-world domains including financial markets. We discuss algorithms that exploit the AIR property, and provide a theoretical analysis for an algorithm based on Fitted-Q Iteration. Finally, we demonstrate that the algorithm outperforms existing offline reinforcement learning algorithms across different data collection policies in simulated and real world environments where the regularity holds.

This two-part paper develops a paradigmatic theory and detailed methods of the joint electricity market design using reinforcement-learning (RL)-based simulation. In Part 2, this theory is further demonstrated by elaborating detailed methods of designing an electricity spot market (ESM), together with a reserved capacity product (RC) in the ancillary service market (ASM) and a virtual bidding (VB) product in the financial market (FM). Following the theory proposed in Part 1, firstly, market design options in the joint market are specified. Then, the Markov game model is developed, in which we show how to incorporate market design options and uncertain risks in model formulation. A multi-agent policy proximal optimization (MAPPO) algorithm is elaborated, as a practical implementation of the generalized market simulation method developed in Part 1. Finally, the case study demonstrates how to pick the best market design options by using some of the market operation performance indicators proposed in Part 1, based on the simulation results generated by implementing the MAPPO algorithm. The impacts of different market design options on market participants' bidding strategy preference are also discussed.