Embodied AI is a recent research area that aims at creating intelligent agents that can move and operate inside an environment. Existing approaches in this field demand the agents to act in completely new and unexplored scenes. However, this setting is far from realistic use cases that instead require executing multiple tasks in the same environment. Even if the environment changes over time, the agent could still count on its global knowledge about the scene while trying to adapt its internal representation to the current state of the environment. To make a step towards this setting, we propose Spot the Difference: a novel task for Embodied AI where the agent has access to an outdated map of the environment and needs to recover the correct layout in a fixed time budget. To this end, we collect a new dataset of occupancy maps starting from existing datasets of 3D spaces and generating a number of possible layouts for a single environment. This dataset can be employed in the popular Habitat simulator and is fully compliant with existing methods that employ reconstructed occupancy maps during navigation. Furthermore, we propose an exploration policy that can take advantage of previous knowledge of the environment and identify changes in the scene faster and more effectively than existing agents. Experimental results show that the proposed architecture outperforms existing state-of-the-art models for exploration on this new setting.

Researchers design multiple strategies for an artificial intelligent (AI) agent to solve a stochastic puzzle like Minesweeper. For decades, efforts in solving games had been exclusive to solving two-player games (i.e., board games like checkers, chess-like games, etc.), where the game outcome can be correctly and efficiently predicted by applying some artificial intelligence (AI) search technique and collecting a massive amount of gameplay statistics. However, such a method and technique cannot be applied directly to the puzzle-solving domain since puzzles are generally played alone (single-player) and have unique characteristics (such as stochastic or hidden information). So then, a question arose as to how the AI technique can retain its performance for solving two-player games but instead applied to a single-agent puzzle? For years, puzzles and games had been regarded as interchangeable or one part of the other.

In the pooled data problem we are given a set of $n$ agents, each of which holds a hidden state bit, either $0$ or $1$. A querying procedure returns for a query set the sum of the states of the queried agents. The goal is to reconstruct the states using as few queries as possible. In this paper we consider two noise models for the pooled data problem. In the noisy channel model, the result for each agent flips with a certain probability. In the noisy query model, each query result is subject to random Gaussian noise. Our results are twofold. First, we present and analyze for both error models a simple and efficient distributed algorithm that reconstructs the initial states in a greedy fashion. Our novel analysis pins down the range of error probabilities and distributions for which our algorithm reconstructs the exact initial states with high probability. Secondly, we present simulation results of our algorithm and compare its performance with approximate message passing (AMP) algorithms that are conjectured to be optimal in a number of related problems.

We study the problem of expert advice under partial bandit feedback setting and create a sequential minimax optimal algorithm. Our algorithm works with a more general partial monitoring setting, where, in contrast to the classical bandit feedback, the losses can be revealed in an adversarial manner. Our algorithm adopts a universal prediction perspective, whose performance is analyzed with regret against a general expert selection sequence. The regret we study is against a general competition class that covers many settings (such as the switching or contextual experts settings) and the expert selection sequences in the competition class are determined by the application at hand. Our regret bounds are second order bounds in terms of the sum of squared losses and the normalized regret of our algorithm is invariant under arbitrary affine transforms of the loss sequence. Our algorithm is truly online and does not use any preliminary information about the loss sequences.

Modern artificial intelligence is capable of wonders. It can produce breathtaking original content: poetry, prose, images, music, human faces. Last year it produced a solution to the "protein folding problem," a grand challenge in biology that has stumped researchers for half a century. Yet today's AI still has fundamental limitations. Relative to what we would expect from a truly intelligent agent--relative to that original inspiration and benchmark for artificial intelligence, human cognition--AI has a long way to go. Critics like to point to these shortcomings as evidence that the pursuit of artificial intelligence is misguided or has failed. The better way to view them, though, is as inspiration: as an inventory of the challenges that will be important to address in order to advance the state of the art in AI.

PLEASE NOTE: This is the first generated blog and each new run of the code will be different. This should not be taken as the ground truth. The mining industry has been globalised for many years, with companies operating in multiple countries to maximise production and profits. However, this has led to a number of challenges, including the need to operate in different regulatory environments, manage different labour forces, and navigate different tax systems. Additionally, the volatility of commodity prices has also led to challenges for the industry. Despite these challenges, the mining industry remains a key driver of globalisation, and offers a number of opportunities for companies looking to expand into new markets.

In this article, we consider a multi-agent path planning problem in a partially impeded environment. The impeded environment is represented by a graph with select road segments (edges) in disrepair impeding vehicular movement in the road network. A convoy wishes to travel from a starting location to a destination while minimizing some accumulated cost. The convoy may traverse an impeded edge for an additional cost (associated with repairing the edge) than if it were unimpeded. A second vehicle, referred to as a service vehicle, is simultaneously deployed with the convoy. The service vehicle assists the convoy by repairing an edge, reducing the cost for the convoy to traverse that edge. The convoy is permitted to wait at any vertex to allow the service vehicle to complete repairing an edge. The service vehicle is permitted to terminate its path at any vertex. The goal is then to find a pair of paths so the convoy reaches its destination while minimizing the total time (cost) the two vehicles are active, including any time the convoy waits. We refer to this problem as the Assisted Shortest Path Problem (ASPP). We present a generalized permanent labeling algorithm to find an optimal solution for the ASPP. We also introduce additional modifications to the labeling algorithm to significantly improve the computation time and refer to the modified labeling algorithm as $GPLA^*$. Computational results are presented to illustrate the effectiveness of $GPLA^*$ in solving the ASPP. We then give concluding remarks and briefly discuss potential variants of the ASPP for future work.

Howie Choset is a Professor of Robotics where he serves as the co-director, along with Matt Travers, of the Biorobotics Lab. Choset's research program has made contributions to strategically significant problems in surgery, manufacturing, on-orbit maintenance, recycling and search and rescue. His work is most famous for its snake robots and other biologically inspired systems and recently his group has been contributing to robotic modularity, multi-agent planning, information-based search, and skill learning. Currently, Choset's projects include: medical support in the field, expeditionary robotics, on-orbit maintenance and construction of structures in space, rapidly carrying heavy objects up several flights of stairs, recycling of E-waste, food preparation, "edge"-sensing, and aerospace painting. Choset has led multi-PI projects centered on manufacturing: (1) automating the programming of robots for auto-body painting; (2) the development of mobile manipulators for agile and flexible fixture-free manufacturing of large structures in aerospace, and (3) the creation of a data-robot ecosystem for rapid manufacturing in the commercial electronics industry.

We then define abstract actions that correspond to control inputs that cause transitions between these regions. Due to the noise, every action has multiple possible outcomes that all occur with a certain probability. We compute lower and upper bounds (intervals) on these probabilities based on a finite number of observations of the noise. Our abstraction procedure ensures that we obtain a faithful, yet abstract representation of the autonomous system. In fact, this abstraction constitutes a type of Markov decision process, which is the standard type of model in sequential decision making under uncertainty. To analyze our abstract models in a rigorous manner, we use state-of-art tools from an area called formal verification.

This is the blog post version of the paper by the same name. Special thanks to Kate Woolverton, Paul Christiano, Rohin Shah, Alex Turner, William Saunders, Beth Barnes, Abram Demski, Scott Garrabrant, Sam Eisenstat, and Tsvi Benson-Tilsen for providing helpful comments and feedback on this post and the talk that preceded it. This post is a collection of 11 different proposals for building safe advanced AI under the current machine learning paradigm. There's a lot of literature out there laying out various different approaches such as amplification, debate, or recursive reward modeling, but a lot of that literature focuses primarily on outer alignment at the expense of inner alignment and doesn't provide direct comparisons between approaches. The goal of this post is to help solve that problem by providing a single collection of 11 different proposals for building safe advanced AI--each including both inner and outer alignment components. That being said, not only does this post not ...