Actor-critic methods, a type of model-free Reinforcement Learning, have beensuccessfully applied to challenging tasks in continuous control, often achievingstate-of-the artperformance.

Personal use of this material is permitted. Abstract-- Real-time control is an essential aspect of safe robot operation in the real world with dynamic objects. We present a framework for the analysis of object-aware controllers, methods for altering a robot's motion to anticipate and avoid possible collisions. This framework is focused on three design considerations: kinematics, motion profiles, and virtual constraints. Additionally, the analysis in this work relies on verification of robot behaviors using fundamental robot-obstacle experimental scenarios. T o showcase the effectiveness of our method we compare three representative object-aware controllers. The comparison uses metrics originating from the design considerations. From the analysis, we find that the design of object-aware controllers often lacks kinematic considerations, continuity of control points, and stability in movement profiles. We conclude that this framework can be used in the future to design, compare, and benchmark obstacle avoidance methods.

Neural Information Processing Systems http://nips.cc/

The reasoning abilities of Large Language Models (LLMs) are becoming a central focus of study in NLP. In this paper, we consider the case of syllogistic reasoning, an area of deductive reasoning studied extensively in logic and cognitive psychology. Previous research has shown that pre-trained LLMs exhibit reasoning biases, such as $\textit{content effects}$, avoid answering that $\textit{no conclusion follows}$, display human-like difficulties, and struggle with multi-step reasoning. We contribute to this research line by systematically investigating the effects of chain-of-thought reasoning, in-context learning (ICL), and supervised fine-tuning (SFT) on syllogistic reasoning, considering syllogisms with conclusions that support or violate world knowledge, as well as ones with multiple premises. Crucially, we go beyond the standard focus on accuracy, with an in-depth analysis of the conclusions generated by the models. Our results suggest that the behavior of pre-trained LLMs can be explained by heuristics studied in cognitive science and that both ICL and SFT improve model performance on valid inferences, although only the latter mitigates most reasoning biases without harming model consistency.

Deployment of Large Language Models (LLMs) has major computational costs, due to their rapidly expanding size. Compression of LLMs reduces the memory footprint, latency, and energy required for their inference. Post-training Quantization (PTQ) techniques have been developed to compress LLMs while avoiding expensive re-training. Most PTQ approaches formulate the quantization error based on a layer-wise $\ell_2$ loss, ignoring the model output. Then, each layer is calibrated using its layer-wise Hessian to update the weights towards minimizing the $\ell_2$ quantization error. The Hessian is also used for detecting the most salient weights to quantization. Such PTQ approaches are prone to accuracy drop in low-precision quantization. We propose Output-adaptive Calibration (OAC) to incorporate the model output in the calibration process. We formulate the quantization error based on the distortion of the output cross-entropy loss. OAC approximates the output-adaptive Hessian for each layer under reasonable assumptions to reduce the computational complexity. The output-adaptive Hessians are used to update the weight matrices and detect the salient weights towards maintaining the model output. Our proposed method outperforms the state-of-the-art baselines such as SpQR and BiLLM, especially, at extreme low-precision (2-bit and binary) quantization.

Communication and computation are often viewed as separate tasks. This approach is very effective from the perspective of engineering as isolated optimizations can be performed. However, for many computation-oriented applications, the main interest is a function of the local information at the devices, rather than the local information itself. In such scenarios, information theoretical results show that harnessing the interference in a multiple access channel for computation, i.e., over-the-air computation (OAC), can provide a significantly higher achievable computation rate than separating communication and computation tasks. Moreover, the gap between OAC and separation in terms of computation rate increases with more participating nodes. Given this motivation, in this study, we provide a comprehensive survey on practical OAC methods. After outlining fundamentals related to OAC, we discuss the available OAC schemes with their pros and cons. We provide an overview of the enabling mechanisms for achieving reliable computation in the wireless channel. Finally, we summarize the potential applications of OAC and point out some future directions.

In split machine learning (ML), different partitions of a neural network (NN) are executed by different computing nodes, requiring a large amount of communication cost. To ease communication burden, over-the-air computation (OAC) can efficiently implement all or part of the computation at the same time of communication. Based on the proposed system, the system implementation over wireless network is introduced and we provide the problem formulation. In particular, we show that the inter-layer connection in a NN of any size can be mathematically decomposed into a set of linear precoding and combining transformations over MIMO channels. Therefore, the precoding matrix at the transmitter and the combining matrix at the receiver of each MIMO link, as well as the channel matrix itself, can jointly serve as a fully connected layer of the NN. The generalization of the proposed scheme to the conventional NNs is also introduced. Finally, we extend the proposed scheme to the widely used convolutional neural networks and demonstrate its effectiveness under both the static and quasi-static memory channel conditions with comprehensive simulations. In such a split ML system, the precoding and combining matrices are regarded as trainable parameters, while MIMO channel matrix is regarded as unknown (implicit) parameters.

Advanced cyberinfrastructure (CI) is critical to science and engineering (S&E) research. For example, over the past two years, CI resources (including those provided by the COVID-19 HPC Consortiuma) enabled research that dramatically accelerated efforts to understand, respond to, and mitigate near- and longer-term impacts of the novel coronavirus disease 2019 (COVID-19) pandemic.b Computer-based epidemiology models informed public policy in the U.S., and in countries throughout the world, and newly studied transmission models for the virus have been used to forecast resource availability and mortality stratified by age group at the county level.c Artificial intelligence and machine learning approaches accelerated drug screening to find candidate medicines from trillions of possible chemical compounds,d and differential gene expressions among COVID-19 patient populations have been analyzed with important implications for treatment planning.e Structural modeling of the virus has led to new insights, speeding the development of vaccines and antigens.

Actor-critic methods, a type of model-free Reinforcement Learning, have been successfully applied to challenging tasks in continuous control, often achieving state-of-the art performance. However, wide-scale adoption of these methods in real-world domains is made difficult by their poor sample efficiency. We address this problem both theoretically and empirically. On the theoretical side, we identify two phenomena preventing efficient exploration in existing state-of-the-art algorithms such as Soft Actor Critic. First, combining a greedy actor update with a pessimistic estimate of the critic leads to the avoidance of actions that the agent does not know about, a phenomenon we call pessimistic underexploration. Second, current algorithms are directionally uninformed, sampling actions with equal probability in opposite directions from the current mean. This is wasteful, since we typically need actions taken along certain directions much more than others. To address both of these phenomena, we introduce a new algorithm, Optimistic Actor Critic, which approximates a lower and upper confidence bound on the state-action value function. This allows us to apply the principle of optimism in the face of uncertainty to perform directed exploration using the upper bound while still using the lower bound to avoid overestimation. We evaluate OAC in several challenging continuous control tasks, achieving state-of the art sample efficiency.