Hierarchical reinforcement learning (HRL) incorporates temporal abstraction into reinforcement learning (RL) by explicitly taking advantage of hierarchical structure. Modern HRL typically designs a hierarchical agent composed of a high-level policy and low-level policies. The high-level policy selects which low-level policy to activate at a lower frequency and the activated low-level policy selects an action at each time step. Recent HRL algorithms have achieved performance gains over standard RL algorithms in synthetic navigation tasks. However, we cannot apply these HRL algorithms to real-world navigation tasks. One of the main challenges is that real-world navigation tasks require an agent to perform safe and interactive behaviors in dynamic environments. In this paper, we propose imagination-augmented HRL (IAHRL) that efficiently integrates imagination into HRL to enable an agent to learn safe and interactive behaviors in real-world navigation tasks. Imagination is to predict the consequences of actions without interactions with actual environments. The key idea behind IAHRL is that the low-level policies imagine safe and structured behaviors, and then the high-level policy infers interactions with surrounding objects by interpreting the imagined behaviors. We also introduce a new attention mechanism that allows our high-level policy to be permutation-invariant to the order of surrounding objects and to prioritize our agent over them. To evaluate IAHRL, we introduce five complex urban driving tasks, which are among the most challenging real-world navigation tasks. The experimental results indicate that IAHRL enables an agent to perform safe and interactive behaviors, achieving higher success rates and lower average episode steps than baselines.

When we design and deploy an Reinforcement Learning (RL) agent, reward functions motivates agents to achieve an objective. An incorrect or incomplete specification of the objective can result in behavior that does not align with human values - failing to adhere with social and moral norms that are ambiguous and context dependent, and cause undesired outcomes such as negative side effects and exploration that is unsafe. Previous work have manually defined reward functions to avoid negative side effects, use human oversight for safe exploration, or use foundation models as planning tools. This work studies the ability of leveraging Large Language Models (LLM)' understanding of morality and social norms on safe exploration augmented RL methods. This work evaluates language model's result against human feedbacks and demonstrates language model's capability as direct reward signals.

Logic synthesis, a pivotal stage in chip design, entails optimizing chip specifications encoded in hardware description languages like Verilog into highly efficient implementations using Boolean logic gates. The process involves a sequential application of logic minimization heuristics ("synthesis recipe"), with their arrangement significantly impacting crucial metrics such as area and delay. Addressing the challenge posed by the broad spectrum of design complexities -- from variations of past designs (e.g., adders and multipliers) to entirely novel configurations (e.g., innovative processor instructions) -- requires a nuanced'synthesis recipe' guided by human expertise and intuition. This study conducts a thorough examination of learning and search techniques for logic synthesis, unearthing a surprising revelation: pre-trained agents, when confronted with entirely novel designs, may veer off course, detrimentally affecting the search trajectory. We present ABC-RL, a meticulously tuned α parameter that adeptly adjusts recommendations from pre-trained agents during the search process. Computed based on similarity scores through nearest neighbor retrieval from the training dataset, ABC-RL yields superior synthesis recipes tailored for a wide array of hardware designs. Our findings showcase substantial enhancements in the Quality-of-result (QoR) of synthesized circuits, boasting improvements of up to 24.8% compared to state-of-the-art techniques. Furthermore, ABC-RL achieves an impressive up to 9x reduction in runtime (iso-QoR) when compared to current state-of-the-art methodologies. Modern chips are designed using sophisticated electronic design automation (EDA) algorithms that automatically convert logic functions expressed in a hardware description language (HDL) like Verilog to a physical layout that can be manufactured at a semiconductor foundry. EDA involves a sequence of steps, the first of which is logic synthesis. Logic synthesis converts HDL into a low-level "netlist" of Boolean logic gates that implement the desired function. A netlist is a graph whose nodes are logic gates (e.g., ANDs, NOTs, ORs) and whose edges represent connections between gates.

Optimal management of cross-asset infrastructure is a complex problem that requires adept inspection and maintenance policies addressing stochastic degradation impacts. According to the 2021 ASCE infrastructure report card [1], the US infrastructure is in fair to poor condition, earning a cumulative grade of C-, with components nearing the end of their useful lives and at high risk of failure. Pavements and bridges are indicative examples of inadequate infrastructure. One in every five miles of pavements is in poor condition, and 7.5% of bridges are structurally deficient. Economic analyses indicate that the US Department of Transportation fell 50% short of the funds required to sustain the national transportation system [1], which is also reflected in the available resources at individual State transportation agencies. The Virginia Department of Transportation, for example, reported that 50% of the State's bridges have exceeded their useful lives, and the required funds to replace them are five times greater than the estimated available funds over the next fifty years [2]. Inspection and Maintenance (I&M) policies are therefore indispensable towards efficiently distributing available economic and environmental resources for transportation systems. Making optimal decisions in complex and uncertain environments presents a variety of difficulties, including heterogeneity of asset classes, a high number of components resulting in vast state and action spaces, unreliable observations, limited availability of resources, and several related risks. Optimal solutions that define inspection and maintenance policies should thus incorporate concepts such as (i) online and offline data learning, (ii) imperfect information support, (iii) stochastic action outcomes considerations, and (iv) optimization of long-term goals under multiple constraints (e.g., safety targets or resource constraints).

Social robot navigation can be helpful in various contexts of daily life but requires safe human-robot interactions and efficient trajectory planning. While modeling pairwise relations has been widely studied in multi-agent interacting systems, the ability to capture larger-scale group-wise activities is limited. In this paper, we propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures, and we demonstrate its effectiveness for multi-agent trajectory prediction and social robot navigation. In addition to the edges between pairs of nodes (i.e., agents), we propose to infer hyperedges that adaptively connect multiple nodes to enable group-wise reasoning in an unsupervised manner. Our approach infers dynamically evolving relation graphs and hypergraphs to capture the evolution of relations, which the trajectory predictor employs to generate future states. Meanwhile, we propose to regularize the sharpness and sparsity of the learned relations and the smoothness of the relation evolution, which proves to enhance training stability and model performance. The proposed approach is validated on synthetic crowd simulations and real-world benchmark datasets. Experiments demonstrate that the approach infers reasonable relations and achieves state-of-the-art prediction performance. In addition, we present a deep reinforcement learning (DRL) framework for social robot navigation, which incorporates relational reasoning and trajectory prediction systematically. In a group-based crowd simulation, our method outperforms the strongest baseline by a significant margin in terms of safety, efficiency, and social compliance in dense, interactive scenarios.

A pervasive phenomenon in machine learning applications is distribution shift, where training and deployment conditions for a machine learning model differ. As distribution shift typically results in a degradation in performance, much attention has been devoted to algorithmic interventions that mitigate these detrimental effects. In this paper, we study the effect of distribution shift in the presence of model misspecification, specifically focusing on $L_{\infty}$-misspecified regression and adversarial covariate shift, where the regression target remains fixed while the covariate distribution changes arbitrarily. We show that empirical risk minimization, or standard least squares regression, can result in undesirable misspecification amplification where the error due to misspecification is amplified by the density ratio between the training and testing distributions. As our main result, we develop a new algorithm -- inspired by robust optimization techniques -- that avoids this undesirable behavior, resulting in no misspecification amplification while still obtaining optimal statistical rates. As applications, we use this regression procedure to obtain new guarantees in offline and online reinforcement learning with misspecification and establish new separations between previously studied structural conditions and notions of coverage.

In this paper, the problem of using one active unmanned aerial vehicle (UAV) and four passive UAVs to localize a 3D target UAV in real time is investigated. In the considered model, each passive UAV receives reflection signals from the target UAV, which are initially transmitted by the active UAV. The received reflection signals allow each passive UAV to estimate the signal transmission distance which will be transmitted to a base station (BS) for the estimation of the position of the target UAV. Due to the movement of the target UAV, each active/passive UAV must optimize its trajectory to continuously localize the target UAV. Meanwhile, since the accuracy of the distance estimation depends on the signal-to-noise ratio of the transmission signals, the active UAV must optimize its transmit power. This problem is formulated as an optimization problem whose goal is to jointly optimize the transmit power of the active UAV and trajectories of both active and passive UAVs so as to maximize the target UAV positioning accuracy. To solve this problem, a Z function decomposition based reinforcement learning (ZD-RL) method is proposed. Compared to value function decomposition based RL (VD-RL), the proposed method can find the probability distribution of the sum of future rewards to accurately estimate the expected value of the sum of future rewards thus finding better transmit power of the active UAV and trajectories for both active and passive UAVs and improving target UAV positioning accuracy. Simulation results show that the proposed ZD-RL method can reduce the positioning errors by up to 39.4% and 64.6%, compared to VD-RL and independent deep RL methods, respectively.

We report an improvements to NeurIPS 2023 HomeRobot: Open Vocabulary Mobile Manipulation (OVMM) Challenge reinforcement learning baseline. More specifically, we propose more accurate semantic segmentation module, along with better place skill policy, and high-level heuristic that outperforms the baseline by 2.4% of overall success rate (sevenfold improvement) and 8.2% of partial success rate (1.75 times improvement) on Test Standard split of the challenge dataset. With aforementioned enhancements incorporated our agent scored 3rd place in the challenge on both simulation and real-world stages.

Evolutionary Reinforcement Learning (ERL), which integrates Evolutionary Algorithms (EAs) and Reinforcement Learning (RL) for optimization, has demonstrated remarkable performance advancements. By fusing the strengths of both approaches, ERL has emerged as a promising research direction. This survey offers a comprehensive overview of the diverse research branches in ERL. Specifically, we systematically summarize recent advancements in relevant algorithms and identify three primary research directions: EA-assisted optimization of RL, RL-assisted optimization of EA, and synergistic optimization of EA and RL. Following that, we conduct an in-depth analysis of each research direction, organizing multiple research branches. We elucidate the problems that each branch aims to tackle and how the integration of EA and RL addresses these challenges. In conclusion, we discuss potential challenges and prospective future research directions across various research directions.

In this work, we propose a Self-Supervised training strategy specifically designed for combinatorial problems. One of the main obstacles in applying supervised paradigms to such problems is the requirement of expensive target solutions as ground-truth, often produced with costly exact solvers. Inspired by Semi- and Self-Supervised learning, we show that it is possible to easily train generative models by sampling multiple solutions and using the best one according to the problem objective as a pseudo-label. In this way, we iteratively improve the model generation capability by relying only on its self-supervision, completely removing the need for optimality information. We prove the effectiveness of this Self-Labeling strategy on the Job Shop Scheduling (JSP), a complex combinatorial problem that is receiving much attention from the Reinforcement Learning community. We propose a generative model based on the well-known Pointer Network and train it with our strategy. Experiments on two popular benchmarks demonstrate the potential of this approach as the resulting models outperform constructive heuristics and current state-of-the-art Reinforcement Learning proposals.