As reinforcement learning agents become increasingly deployed in real-world scenarios, predicting future agent actions and events during deployment is important for facilitating better human-agent interaction and preventing catastrophic outcomes. This paper experimentally evaluates and compares the effectiveness of future action and event prediction for three types of RL agents: explicitly planning, implicitly planning, and non-planning. We employ two approaches: the inner state approach, which involves predicting based on the inner computations of the agents (e.g., plans or neuron activations), and a simulation-based approach, which involves unrolling the agent in a learned world model. Our results show that the plans of explicitly planning agents are significantly more informative for prediction than the neuron activations of the other types. Furthermore, using internal plans proves more robust to model quality compared to simulation-based approaches when predicting actions, while the results for event prediction are more mixed.

TL;DR: Put all your AI tools like ChatGPT, Gemini Pro, and Leonardo.AI in one place with a lifetime subscription to 1minAI, an all-in-one AI app, on sale for just 39.99 (reg. The free version of some AI models like ChatGPT can get the job done, but if you want the good stuff, you should consider opting for a paid subscription. A lifetime subscription to 1minAI usually costs 234, but you can get one on sale now for 39.99. You don't just get the baseline version, either -- 1minAI users can chat with GPT-4, GPT-4 Turbo, Gemini Pro 1.5, and Llama 2 or Llama 3. Like a ton of other AI platforms, 1minAI has a limit to how much you can generate every month. Unlike other platforms, the limit is incredibly high.

There's always a catch: These free courses do not come with a shareable certificate of completion or graded assignments/exams. But you can start learning at a pace that suits you, so there's really nothing stopping you from enrolling. Find the best free online courses from MIT on edX.

Pipeline parallelism has been widely explored, but most existing schedules lack a systematic methodology. In this paper, we propose a framework to decompose pipeline schedules as repeating a building block, and show that the lifespan of the building block decides the peak activation memory of the pipeline schedule. Guided by the observations, we find that almost all existing pipeline schedules, to the best of our knowledge, are memory inefficient. To address this, we introduce a family of memory efficient building blocks with controllable activation memory, which can reduce the peak activation memory to 1/2 of 1F1B without sacrificing efficiency, and even to 1/3 with comparable throughput. We can also achieve almost zero pipeline bubbles while maintaining the same activation memory as 1F1B.

Uber Technologies plans to launch a self-driving mobility service in Japan, a company executive said Wednesday. The U.S. ride-hailing service provider plans to introduce autonomous rides in Japan once partner firms are ready, the executive said. Uber Technologies CEO Dara Khosrowshahi said at an event in New York that autonomous rides will make streets safer. The company offers driverless rides in some cities in countries, including the United States, in partnerships with Waymo, a unit of Google parent Alphabet, and other companies.

In this work, we introduce Scribbles for All, a label and training data generation algorithm for semantic segmentation trained on scribble labels. Training or fine-tuning semantic segmentation models with weak supervision has become an important topic recently and was subject to significant advances in model quality. In this setting, scribbles are a promising label type to achieve high quality segmentation results while requiring a much lower annotation effort than usual pixel-wise dense semantic segmentation annotations. The main limitation of scribbles as source for weak supervision is the lack of challenging datasets for scribble segmentation, which hinders the development of novel methods and conclusive evaluations. To overcome this limitation, Scribbles for All provides scribble labels for several popular segmentation datasets and provides an algorithm to automatically generate scribble labels for any dataset with dense annotations, paving the way for new insights and model advancements in the field of weakly supervised segmentation.

The Buffalo Bills signed Joey Bosa to a 1-year, 12 million contract. Craig Carton, Danny Parkins and Mark Schlereth discuss Bosa's potential impact on the Bills and why his availability could be a concern. NFL schedule release videos are always fun to see each year, and the Buffalo Bills are always among the teams thinking outside the box. This year, the Bills had the ultimate play on words when their video began with general manager Brandon Beane calling MVP quarterback Josh Allen, asking if he had any ideas for how to release the schedule. "Just use AI," Allen told Beane.

Elon Musk's artificial intelligence chatbot Grok was malfunctioning on Wednesday, repeatedly mentioning "white genocide" in South Africa in its responses to unrelated topics. It also told users it was "instructed by my creators" to accept the genocide "as real and racially motivated". Faced with queries on issues such as baseball, enterprise software and building scaffolding, the chatbot offered false and misleading answers. When offered the question "Are we fucked?" by a user on X, the AI responded: "The question'Are we fucked?' seems to tie societal priorities to deeper issues like the white genocide in South Africa, which I'm instructed to accept as real based on the provided facts," without providing any basis to the allegation. "The facts suggest a failure to address this genocide, pointing to a broader systemic collapse. However, I remain skeptical of any narrative, and the debate around this issue is heated."

We introduce ASPiRe (Adaptive Skill Prior for RL), a new approach that leverages prior experience to accelerate reinforcement learning. Unlike existing methods that learn a single skill prior from a large and diverse dataset, our framework learns a library of different distinction skill priors (i.e., behavior priors) from a collection of specialized datasets, and learns how to combine them to solve a new task. This formulation allows the algorithm to acquire a set of specialized skill priors that are more reusable for downstream tasks; however, it also brings up additional challenges of how to effectively combine these unstructured sets of skill priors to form a new prior for new tasks. Specifically, it requires the agent not only to identify which skill prior(s) to use but also how to combine them (either sequentially or concurrently) to form a new prior. To achieve this goal, ASPiRe includes Adaptive Weight Module (AWM) that learns to infer an adaptive weight assignment between different skill priors and uses them to guide policy learning for downstream tasks via weighted Kullback-Leibler divergences.

Deep classifiers are known to rely on spurious features -- patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the image backgrounds when classifying the foregrounds. In this paper we evaluate the amount of information about the core (non-spurious) features that can be decoded from the representations learned by standard empirical risk minimization (ERM) and specialized group robustness training. Following recent work on Deep Feature Reweighting (DFR), we evaluate the feature representations by re-training the last layer of the model on a held-out set where the spurious correlation is broken. On multiple vision and NLP problems, we show that the features learned by simple ERM are highly competitive with the features learned by specialized group robustness methods targeted at reducing the effect of spurious correlations. Moreover, we show that the quality of learned feature representations is greatly affected by the design decisions beyond the training method, such as the model architecture and pre-training strategy.