The advent of autonomous vehicles (AVs) alongside human-driven vehicles (HVs) has ushered in an era of mixed traffic flow, presenting a significant challenge: the intricate interaction between these entities within complex driving environments. AVs are expected to have human-like driving behavior to seamlessly integrate into human-dominated traffic systems. To address this issue, we propose a reinforcement learning framework that considers driving priors and Social Coordination Awareness (SCA) to optimize the behavior of AVs. The framework integrates a driving prior learning (DPL) model based on a variational autoencoder to infer the driver's driving priors from human drivers' trajectories. A policy network based on a multi-head attention mechanism is designed to effectively capture the interactive dependencies between AVs and other traffic participants to improve decision-making quality. The introduction of SCA into the autonomous driving decision-making system, and the use of Coordination Tendency (CT) to quantify the willingness of AVs to coordinate the traffic system is explored. Simulation results show that the proposed framework can not only improve the decision-making quality of AVs but also motivate them to produce social behaviors, with potential benefits for the safety and traffic efficiency of the entire transportation system.

Controlled execution of dynamic motions in quadrupedal robots, especially those with articulated soft bodies, presents a unique set of challenges that traditional methods struggle to address efficiently. In this study, we tackle these issues by relying on a simple yet effective two-stage learning framework to generate dynamic motions for quadrupedal robots. First, a gradient-free evolution strategy is employed to discover simply represented control policies, eliminating the need for a predefined reference motion. Then, we refine these policies using deep reinforcement learning. Our approach enables the acquisition of complex motions like pronking and back-flipping, effectively from scratch. Additionally, our method simplifies the traditionally labour-intensive task of reward shaping, boosting the efficiency of the learning process. Importantly, our framework proves particularly effective for articulated soft quadrupeds, whose inherent compliance and adaptability make them ideal for dynamic tasks but also introduce unique control challenges.

The open radio access network (O-RAN) architecture supports intelligent network control algorithms as one of its core capabilities. Data-driven applications incorporate such algorithms to optimize radio access network (RAN) functions via RAN intelligent controllers (RICs). Deep reinforcement learning (DRL) algorithms are among the main approaches adopted in the O-RAN literature to solve dynamic radio resource management problems. However, despite the benefits introduced by the O-RAN RICs, the practical adoption of DRL algorithms in real network deployments falls behind. This is primarily due to the slow convergence and unstable performance exhibited by DRL agents upon deployment and when encountering previously unseen network conditions. In this paper, we address these challenges by proposing transfer learning (TL) as a core component of the training and deployment workflows for the DRL-based closed-loop control of O-RAN functionalities. To this end, we propose and design a hybrid TL-aided approach that leverages the advantages of both policy reuse and distillation TL methods to provide safe and accelerated convergence in DRL-based O-RAN slicing. We conduct a thorough experiment that accommodates multiple services, including real VR gaming traffic to reflect practical scenarios of O-RAN slicing. We also propose and implement policy reuse and distillation-aided DRL and non-TL-aided DRL as three separate baselines. The proposed hybrid approach shows at least: 7.7% and 20.7% improvements in the average initial reward value and the percentage of converged scenarios, and a 64.6% decrease in reward variance while maintaining fast convergence and enhancing the generalizability compared with the baselines.

A key challenge for a reinforcement learning (RL) agent is to incorporate external/expert1 advice in its learning. The desired goals of an algorithm that can shape the learning of an RL agent with external advice include (a) maintaining policy invariance; (b) accelerating the learning of the agent; and (c) learning from arbitrary advice [3]. To address this challenge this paper formulates the problem of incorporating external advice in RL as a multi-armed bandit called shaping-bandits. The reward of each arm of shaping bandits corresponds to the return obtained by following the expert or by following a default RL algorithm learning on the true environment reward.We show that directly applying existing bandit and shaping algorithms that do not reason about the non-stationary nature of the underlying returns can lead to poor results. Thus we propose UCB-PIES (UPIES), Racing-PIES (RPIES), and Lazy PIES (LPIES) three different shaping algorithms built on different assumptions that reason about the long-term consequences of following the expert policy or the default RL algorithm. Our experiments in four different settings show that these proposed algorithms achieve the above-mentioned goals whereas the other algorithms fail to do so.

We consider online reinforcement learning in episodic Markov decision process (MDP) with unknown transition function and stochastic rewards drawn from some fixed but unknown distribution. The learner aims to learn the optimal policy and minimize their regret over a finite time horizon through interacting with the environment. We devise a simple and efficient model-based algorithm that achieves $\widetilde{O}(LX\sqrt{TA})$ regret with high probability, where $L$ is the episode length, $T$ is the number of episodes, and $X$ and $A$ are the cardinalities of the state space and the action space, respectively. The proposed algorithm, which is based on the concept of ``optimism in the face of uncertainty", maintains confidence sets of transition and reward functions and uses occupancy measures to connect the online MDP with linear programming. It achieves a tighter regret bound compared to the existing works that use a similar confidence set framework and improves computational effort compared to those that use a different framework but with a slightly tighter regret bound.

Over the recent years, Reinforcement Learning combined with Deep Learning techniques has successfully proven to solve complex problems in various domains, including robotics, self-driving cars, and finance. In this paper, we are introducing Reinforcement Learning (RL) to label placement, a complex task in data visualization that seeks optimal positioning for labels to avoid overlap and ensure legibility. Our novel point-feature label placement method utilizes Multi-Agent Deep Reinforcement Learning to learn the label placement strategy, the first machine-learning-driven labeling method, in contrast to the existing hand-crafted algorithms designed by human experts. To facilitate RL learning, we developed an environment where an agent acts as a proxy for a label, a short textual annotation that augments visualization. Our results show that the strategy trained by our method significantly outperforms the random strategy of an untrained agent and the compared methods designed by human experts in terms of completeness (i.e., the number of placed labels). The trade-off is increased computation time, making the proposed method slower than the compared methods. Nevertheless, our method is ideal for scenarios where the labeling can be computed in advance, and completeness is essential, such as cartographic maps, technical drawings, and medical atlases. Additionally, we conducted a user study to assess the perceived performance. The outcomes revealed that the participants considered the proposed method to be significantly better than the other examined methods. This indicates that the improved completeness is not just reflected in the quantitative metrics but also in the subjective evaluation by the participants.

Directed Exploration is a crucial challenge in reinforcement learning (RL), especially when rewards are sparse. Information-directed sampling (IDS), which optimizes the information ratio, seeks to do so by augmenting regret with information gain. However, estimating information gain is computationally intractable or relies on restrictive assumptions which prohibit its use in many practical instances. In this work, we posit an alternative exploration incentive in terms of the integral probability metric (IPM) between a current estimate of the transition model and the unknown optimal, which under suitable conditions, can be computed in closed form with the kernelized Stein discrepancy (KSD). Based on KSD, we develop a novel algorithm \algo: \textbf{STE}in information dir\textbf{E}cted exploration for model-based \textbf{R}einforcement Learn\textbf{ING}. To enable its derivation, we develop fundamentally new variants of KSD for discrete conditional distributions. {We further establish that {\algo} archives sublinear Bayesian regret, improving upon prior learning rates of information-augmented MBRL.} Experimentally, we show that the proposed algorithm is computationally affordable and outperforms several prior approaches.

When transferring a Deep Reinforcement Learning model from simulation to the real world, the performance could be unsatisfactory since the simulation cannot imitate the real world well in many circumstances. This results in a long period of fine-tuning in the real world. This paper proposes a self-supervised vision-based DRL method that allows robots to pick and place objects effectively and efficiently when directly transferring a training model from simulation to the real world. A height-sensitive action policy is specially designed for the proposed method to deal with crowded and stacked objects in challenging environments. The training model with the proposed approach can be applied directly to a real suction task without any fine-tuning from the real world while maintaining a high suction success rate. It is also validated that our model can be deployed to suction novel objects in a real experiment with a suction success rate of 90\% without any real-world fine-tuning. The experimental video is available at: https://youtu.be/jSTC-EGsoFA.

Abstract-- Reinforcement learning-based policies for continuous control robotic navigation tasks often fail to adapt to changes in the environment during real-time deployment, which may result in catastrophic failures. To address this limitation, we propose a novel approach called RE-MOVE (REquest help and MOVE on) to adapt already trained policy to real-time changes in the environment without re-training via utilizing a language-based feedback. The proposed approach essentially boils down to addressing two main challenges of (1) when to ask for feedback and, if received, (2) how to incorporate feedback into trained policies. RE-MOVE incorporates an epistemic uncertainty-based framework to determine the optimal time to request instructions-based feedback. This figure shows robot navigation using our RE-MOVE processing (NLP) paradigm with efficient, prompt design and approach with a language-based feedback scenario. To in dynamic scenes, RE-MOVE identifies the uncertainties show the efficacy of the proposed approach, we performed that appear in the observation space (i.e., a LiDAR laser scanbased extensive synthetic and real-world evaluations in several testtime 2D cost map in our context) and requests assistance from a dynamic navigation scenarios. Such assistance is essential in scenarios where the laser scan in up to 80% enhancement in the attainment of successful goals, misleadingly detects pliable regions (i.e., perceptually deceptive yet coupled with a reduction of 13.50% in the normalized trajectory navigable objects such as hanging clothes, curtains, thin tall grass, length, as compared to alternative approaches, particularly in etc.) as solid obstacles due to the sensing limitations of the LiDAR. To tackle this, we quantify epistemic uncertainty Reinforcement learning (RL) has gained popularity for precisely, considering specific design considerations within navigating complex, dynamic environments [1].

Theory and application of stochastic approximation (SA) has grown within the control systems community since the earliest days of adaptive control. This paper takes a new look at the topic, motivated by recent results establishing remarkable performance of SA with (sufficiently small) constant step-size $\alpha>0$. If averaging is implemented to obtain the final parameter estimate, then the estimates are asymptotically unbiased with nearly optimal asymptotic covariance. These results have been obtained for random linear SA recursions with i.i.d. coefficients. This paper obtains very different conclusions in the more common case of geometrically ergodic Markovian disturbance: (i) The $\textit{target bias}$ is identified, even in the case of non-linear SA, and is in general non-zero. The remaining results are established for linear SA recursions: (ii) the bivariate parameter-disturbance process is geometrically ergodic in a topological sense; (iii) the representation for bias has a simpler form in this case, and cannot be expected to be zero if there is multiplicative noise; (iv) the asymptotic covariance of the averaged parameters is within $O(\alpha)$ of optimal. The error term is identified, and may be massive if mean dynamics are not well conditioned. The theory is illustrated with application to TD-learning.