The ability for an agent to continuously learn new skills without catastrophically forgetting existing knowledge is of critical importance for the development of generally intelligent agents. Most methods devised to address this problem depend heavily on well-defined task boundaries, and thus depend on human supervision. Our task-agnostic method, Self-Activating Neural Ensembles (SANE), uses a modular architecture designed to avoid catastrophic forgetting without making any such assumptions. At the beginning of each trajectory, a module in the SANE ensemble is activated to determine the agent's next policy. During training, new modules are created as needed and only activated modules are updated to ensure that unused modules remain unchanged. This system enables our method to retain and leverage old skills, while growing and learning new ones. We demonstrate our approach on visually rich procedurally generated environments.

Progress in continual reinforcement learning has been limited due to several barriers to entry: missing code, high compute requirements, and a lack of suitable benchmarks. In this work, we present CORA, a platform for Continual Reinforcement Learning Agents that provides benchmarks, baselines, and metrics in a single code package. The benchmarks we provide are designed to evaluate different aspects of the continual RL challenge, such as catastrophic forgetting, plasticity, ability to generalize, and sample-efficient learning. Three of the benchmarks utilize video game environments (Atari, Procgen, NetHack). The fourth benchmark, CHORES, consists of four different task sequences in a visually realistic home simulator, drawn from a diverse set of task and scene parameters. To compare continual RL methods on these benchmarks, we prepare three metrics in CORA: Continual Evaluation, Isolated Forgetting, and Zero-Shot Forward Transfer. Finally, CORA includes a set of performant, open-source baselines of existing algorithms for researchers to use and expand on. We release CORA and hope that the continual RL community can benefit from our contributions, to accelerate the development of new continual RL algorithms.

许多生物，包括各种种类的蜘蛛和毛毛虫，都会改变其形状以切换步态并适应不同的环境。从可拉伸电路到高度变形的软机器人，最近的技术进步已经开始使变化的机器人成为可能。但是，目前尚不清楚应如何以及何时发生变化以及可以获得哪些功能，从而导致各种未解决的设计和控制问题。为了开始解决这些问题，我们在这里模拟，设计和构建一个软机器人，该机器人利用形状变化来在平坦和倾斜的表面上实现运动。在模拟中对该机器人进行建模，我们在两个环境中探索了它的功能，并证明了特定于环境特定形状和步态的存在，这些形状和步态成功地转移到了物理硬件中。我们发现，改变形状的机器人在模拟和现实中比等效但不正确的机器人更好地遍历这些环境。

Real-world datasets exhibit imbalances of varying types and degrees. Several techniques based on re-weighting and margin adjustment of loss are often used to enhance the performance of neural networks, particularly on minority classes. In this work, we analyze the class-imbalanced learning problem by examining the loss landscape of neural networks trained with re-weighting and margin-based techniques. Specifically, we examine the spectral density of Hessian of class-wise loss, through which we observe that the network weights converge to a saddle point in the loss landscapes of minority classes. Following this observation, we also find that optimization methods designed to escape from saddle points can be effectively used to improve generalization on minority classes. We further theoretically and empirically demonstrate that Sharpness-Aware Minimization (SAM), a recent technique that encourages convergence to a flat minima, can be effectively used to escape saddle points for minority classes. Using SAM results in a 6.2\% increase in accuracy on the minority classes over the state-of-the-art Vector Scaling Loss, leading to an overall average increase of 4\% across imbalanced datasets. The code is available at: https://github.com/val-iisc/Saddle-LongTail.

In this paper, we present the Circular Accessible Depth (CAD), a robust traversability representation for an unmanned ground vehicle (UGV) to learn traversability in various scenarios containing irregular obstacles. To predict CAD, we propose a neural network, namely CADNet, with an attention-based multi-frame point cloud fusion module, Stability-Attention Module (SAM), to encode the spatial features from point clouds captured by LiDAR. CAD is designed based on the polar coordinate system and focuses on predicting the border of traversable area. Since it encodes the spatial information of the surrounding environment, which enables a semi-supervised learning for the CADNet, and thus desirably avoids annotating a large amount of data. Extensive experiments demonstrate that CAD outperforms baselines in terms of robustness and precision. We also implement our method on a real UGV and show that it performs well in real-world scenarios.

The high feature dimensionality is a challenge in music emotion recognition. There is no common consensus on a relation between audio features and emotion. The MER system uses all available features to recognize emotion; however, this is not an optimal solution since it contains irrelevant data acting as noise. In this paper, we introduce a feature selection approach to eliminate redundant features for MER. We created a Selected Feature Set (SFS) based on the feature selection algorithm (FSA) and benchmarked it by training with two models, Support Vector Regression (SVR) and Random Forest (RF) and comparing them against with using the Complete Feature Set (CFS). The result indicates that the performance of MER has improved for both Random Forest (RF) and Support Vector Regression (SVR) models by using SFS. We found using FSA can improve performance in all scenarios, and it has potential benefits for model efficiency and stability for MER task.

Salient object detection (SOD) aims to determine the most visually attractive objects in an image. With the development of virtual reality technology, 360{\deg} omnidirectional image has been widely used, but the SOD task in 360{\deg} omnidirectional image is seldom studied due to its severe distortions and complex scenes. In this paper, we propose a Multi-Projection Fusion and Refinement Network (MPFR-Net) to detect the salient objects in 360{\deg} omnidirectional image. Different from the existing methods, the equirectangular projection image and four corresponding cube-unfolding images are embedded into the network simultaneously as inputs, where the cube-unfolding images not only provide supplementary information for equirectangular projection image, but also ensure the object integrity of the cube-map projection. In order to make full use of these two projection modes, a Dynamic Weighting Fusion (DWF) module is designed to adaptively integrate the features of different projections in a complementary and dynamic manner from the perspective of inter and intra features. Furthermore, in order to fully explore the way of interaction between encoder and decoder features, a Filtration and Refinement (FR) module is designed to suppress the redundant information between the feature itself and the feature. Experimental results on two omnidirectional datasets demonstrate that the proposed approach outperforms the state-of-the-art methods both qualitatively and quantitatively.

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

Recent methods in self-supervised learning have demonstrated that masking-based pretext tasks extend beyond NLP, serving as useful pretraining objectives in computer vision. However, existing approaches apply random or ad hoc masking strategies that limit the difficulty of the reconstruction task and, consequently, the strength of the learnt representations. We improve upon current state-of-the-art work in learning adversarial masks by proposing a new framework that generates masks in a sequential fashion with different constraints on the adversary. This leads to improvements in performance on various downstream tasks, such as classification on ImageNet100, STL10, and CIFAR10/100 and segmentation on Pascal VOC. Our results further demonstrate the promising capabilities of masking-based approaches for SSL in computer vision.

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs. The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'. The process involves both a supervised learning and a reinforcement learning phase. In the supervised phase we sample from an initial model, then generate self-critiques and revisions, and then finetune the original model on revised responses. In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences. We then train with RL using the preference model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a result we are able to train a harmless but non-evasive AI assistant that engages with harmful queries by explaining its objections to them. Both the SL and RL methods can leverage chain-of-thought style reasoning to improve the human-judged performance and transparency of AI decision making. These methods make it possible to control AI behavior more precisely and with far fewer human labels.