Many real-world domains require safe decision making in uncertain environments. In this work, we introduce a deep reinforcement learning framework for approaching this important problem. We consider a distribution over transition models, and apply a risk-averse perspective towards model uncertainty through the use of coherent distortion risk measures. We provide robustness guarantees for this framework by showing it is equivalent to a specific class of distributionally robust safe reinforcement learning problems. Unlike existing approaches to robustness in deep reinforcement learning, however, our formulation does not involve minimax optimization. This leads to an efficient, model-free implementation of our approach that only requires standard data collection from a single training environment. In experiments on continuous control tasks with safety constraints, we demonstrate that our framework produces robust performance and safety at deployment time across a range of perturbed test environments.

Table 7: Extensions of Table 1 with more details of prompts used to generate class-conditioned texts for different GLUE tasks. SST-2 and CoLA are single-sequence classification tasks and the rest are sequence-pair classification tasks. Generation for CoLA does not use prompts but by varying sampling temperatures. Text generation with CTRL [23] requires starting with control codes, and we use the ones that correspond to the pretraining corpus where the first sequence is sampled: For MNLI, RTE and MRPC, the first sequence is sampled from Wikipedia; for QNLI and QQP, the first sequence is sampled from OpenWebText [17]. The prompts used for SST-2 are part of the CTRL [23] codes. Furthermore, xg contradiction There is a rumor that xs.

Dendritic updates Complete versions of the dendritic update rules (summarised in Eqns (2) & (3)) are given below. This is valid in our regime where the environmental latent updates slowly compared to neural timescales. The notation we're using admits the possible presence of biases as well as the weights (though biases typically aren't used) by assuming a row of constant 1's could be added to the synaptic inputs effectively absorbing a bias into the weight matrix without loss of generality, for example wgB p(t) wgB p(t)+ bgB . Somatic updates Somatic updates rules (Eqns (4) & (5)) and are repeated here for completeness: p(t)= (t)pB(t)+(1 (t))pA(t) g(t)= (t)gB(t)+(1 (t))gA(t). Update ordering For this hierarchical network of multicompartmental neurons we must specify the order in which we perform these discrete updates to the different layers and the different compartments within these layers.

Advances in generative models have recently revolutionised machine learning. Meanwhile, in neuroscience, generative models have long been thought fundamental to animal intelligence. Understanding the biological mechanisms that support these processes promises to shed light on the relationship between biological and artificial intelligence. In animals, the hippocampal formation is thought to learn and use a generative model to support its role in spatial and non-spatial memory. Here we introduce a biologically plausible model of the hippocampal formation tantamount to a Helmholtz machine that we apply to a temporal stream of inputs. A novel component of our model is that fast theta-band oscillations (5-10 Hz) gate the direction of information flow throughout the network, training it akin to a high-frequency wake-sleep algorithm. Our model accurately infers the latent state of high-dimensional sensory environments and generates realistic sensory predictions. Furthermore, it can learn to path integrate by developing a ring attractor connectivity structure matching previous theoretical proposals and flexibly transfer this structure between environments.

The existing analysis of asynchronous stochastic gradient descent (SGD) degrades dramatically when any delay is large, giving the impression that performance depends primarily on the delay. On the contrary, we prove much better guarantees for the same asynchronous SGD algorithm regardless of the delays in the gradients, depending instead just on the number of parallel devices used to implement the algorithm. Our guarantees are strictly better than the existing analyses, and we also argue that asynchronous SGD outperforms synchronous minibatch SGD in the settings we consider. For our analysis, we introduce a novel recursion based on "virtual iterates" and delay-adaptive stepsizes, which allow us to derive state-of-theart guarantees for both convex and non-convex objectives.

While Explainable Artificial Intelligence (XAI) techniques have been widely studied to explain predictions made by deep neural networks, the way to evaluate the faithfulness of explanation results remains challenging, due to the heterogeneity of explanations for various models and the lack of ground-truth explanations. This paper introduces an XAI benchmark named M4, which allows evaluating various input feature attribution methods using the same set of faithfulness metrics across multiple data modalities (images and texts) and network structures (ResNets, MobileNets, Transformers). A taxonomy for the metrics has been proposed as well. We first categorize commonly used XAI evaluation metrics into three groups based on the ground truth they require. We then implement classic and state-of-the-art feature attribution methods using InterpretDL and conduct extensive experiments to compare methods and gain insights. Extensive experiments have been conducted to provide holistic evaluations as benchmark baselines. Several interesting observations are made for designing attribution algorithms.