ENSO affects the North Atlantic Oscillation 1 year later.

We demonstrate a 1-year lagged extratropical response to the El Niño-Southern Oscillation (ENSO) in observational analyses and climate models. The response maps onto the Arctic Oscillation and is strongest in the North Atlantic, where it resembles the North Atlantic Oscillation (NAO). Unexpectedly, these 1-year lagged teleconnections are at least as strong as the better-known simultaneous winter connections. However, the 1-year lagged response is oppositein sign to the simultaneous response such that 1 year later, El Niño is followed by a positive NAO, whereas La Niña is followed by a negative NAO. The lagged response may also interfere with simultaneous ENSO teleconnections. We show here that these effects are unlikely to be caused by residual aliasing of ENSO cycles; rather, slowly migrating atmospheric angular momentum anomalies explain both the sign and the timing of the extratropical response. Our results have implications for understanding ENSO teleconnections, explaining observed extratropical climate variability and interpreting seasonal to interannual climate predictions.

GeneWorker: An end-to-end robotic reinforcement learning approach with collaborative generator and worker networks.

Reinforcement learning aided by the skill conception exhibits potent capabilities in guiding autonomous agents toward acquiring meaningful behaviors. However, in the current landscape of reinforcement learning, a skill is often merely a rudimentary abstraction of a sequence of primitive actions, serving as a component of the input to policy networks with fixed network parameters. This rigid methodology presents obstacles when attempting to integrate with burgeoning techniques such as meta-learning and large language models. To address this issue, we introduce a unique neural skill representation that abstracts the activation of neurons in each neural layer. Based on this, a novel end-to-end robotic reinforcement learning algorithm is proposed, in which two sub-networks, i.e., generator and worker networks, implement collaborative inferences via neural skills. Specifically, the generator produces a series of multi-spatial neural skills, providing efficient guidance for subsequent decision-making; by integrating these skills, the worker can determine its own network weights and biases to cope with various environmental conditions. Therefore, actions can be sampled with flexibly changeable network parameters through the collaboration between generator and worker networks. The experiments demonstrate that GeneWorker can achieve a mean success rate of over 90.67% on continuous robotic tasks and outperforms previous state-of-the-art methods by a minimum of 54% on the pick-and-place task.