The proliferation of pretrained models, as a result of advancements in pretraining techniques, has led to the emergence of a vast zoo of publicly available models. Effectively utilizing these resources to obtain models with robust out-of-distribution generalization capabilities for downstream tasks has become a crucial area of research. Previous research has primarily focused on identifying the most powerful models within the model zoo, neglecting to fully leverage the diverse inductive biases contained within. This paper argues that the knowledge contained in weaker models is valuable and presents a method for leveraging the diversity within the model zoo to improve out-of-distribution generalization capabilities. Specifically, we investigate the behaviors of various pretrained models across different domains of downstream tasks by characterizing the variations in their encoded representations in terms of two dimensions: diversity shift and correlation shift. This characterization enables us to propose a new algorithm for integrating diverse pretrained models, not limited to the strongest models, in order to achieve enhanced out-of-distribution generalization performance. Our proposed method demonstrates state-of-the-art empirical results on a variety of datasets, thus validating the benefits of utilizing diverse knowledge.

A fundamental objective in reinforcement learning is the maintenance of a proper balance between exploration and exploitation. This problem becomes more challenging when the agent can only partially observe the states of its environment. In this paper we propose a dual-policy method for jointly learning the agent behavior and the balance between exploration exploitation, in partially observable environments. The method subsumes traditional exploration, in which the agent takes actions to gather information about the environment, and active learning, in which the agent queries an oracle for optimal actions (with an associated cost for employing the oracle). The form of the employed exploration is dictated by the specific problem.

A fundamental objective in reinforcement learning is the maintenance of a proper balance between exploration and exploitation. This problem becomes more challenging when the agent can only partially observe the states of its environment. In this paper we propose a dual-policy method for jointly learning the agent behavior and the balance between exploration exploitation, in partially observable environments. The method subsumes traditional exploration, in which the agent takes actions to gather information about the environment, and active learning, in which the agent queries an oracle for optimal actions (with an associated cost for employing the oracle). The form of the employed exploration is dictated by the specific problem.

The advancements in the domain of Artificial Intelligence (AI) are accelerating the business transformation. The old and conventional way of working and operating a business is no longer a success mantra. AI ecosystem enables people and machine to collaborate in a novel way. Moreover, the processes and tasks are getting automated, which in turn, changing the inherent nature of human work. In a recent study done by a large consultancy firm, it was found that the economic contribution of AI to the global community is worth US$ 15.7 trillion by 2030.

Has Netflix's sizeable investment in original science-fiction movies been a bust? By one popular metric, Rotten Tomatoes, the answer would seem to be: Categorically. Since 2017's Okja, a feisty ecological fairy tale by Korean filmmaker Bong Joon-ho, Netflix has put out seven back-to-back stinkers, their average "freshness" score rounding up to 30 percent. Only one of the seven can be called unwatchable: Duncan Jones' Mute, an overlong and sexually confused nightclub noir that trips over itself to imagine a neon-colored vision of future Berlin peopled by the likes of a mustachioed Paul Rudd. This is terribly sad, considering the director's first two films, Moon and Source Code, were the exact opposite--careful, contained stories that played out in modest settings.