There have been predictions that Robots will take over our jobs. As of today, that prediction is rapidly coming to pass. Our imagination may tell us these robots are hardware, machines made of metal or carbon fibre. This is not quite the case, as these Robots are software called bots. Bots are programmed to repetitively automate operational and transactional tasks without the need for human input.

Machine learning has achieved tremendous success in a variety of domains in recent years. However, a lot of these success stories have been in places where the training and the testing distributions are extremely similar to each other. In everyday situations when models are tested in slightly different data than they were trained on, ML algorithms can fail spectacularly. This research attempts to formally define this problem, what sets of assumptions are reasonable to make in our data and what kind of guarantees we hope to obtain from them. Then, we focus on a certain class of out of distribution problems, their assumptions, and introduce simple algorithms that follow from these assumptions that are able to provide more reliable generalization. A central topic in the thesis is the strong link between discovering the causal structure of the data, finding features that are reliable (when using them to predict) regardless of their context, and out of distribution generalization.

Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosity about these unknown instances aids in learning about them, when the corresponding knowledge is eventually available. This motivates us to propose a novel computer vision problem called: `Open World Object Detection', where a model is tasked to: 1) identify objects that have not been introduced to it as `unknown', without explicit supervision to do so, and 2) incrementally learn these identified unknown categories without forgetting previously learned classes, when the corresponding labels are progressively received. We formulate the problem, introduce a strong evaluation protocol and provide a novel solution, which we call ORE: Open World Object Detector, based on contrastive clustering and energy based unknown identification. Our experimental evaluation and ablation studies analyze the efficacy of ORE in achieving Open World objectives. As an interesting by-product, we find that identifying and characterizing unknown instances helps to reduce confusion in an incremental object detection setting, where we achieve state-of-the-art performance, with no extra methodological effort. We hope that our work will attract further research into this newly identified, yet crucial research direction.

One crucial objective of multi-task learning is to align distributions across tasks so that the information between them can be transferred and shared. However, existing approaches only focused on matching the marginal feature distribution while ignoring the semantic information, which may hinder the learning performance. To address this issue, we propose to leverage the label information in multi-task learning by exploring the semantic conditional relations among tasks. We first theoretically analyze the generalization bound of multi-task learning based on the notion of Jensen-Shannon divergence, which provides new insights into the value of label information in multi-task learning. Our analysis also leads to a concrete algorithm that jointly matches the semantic distribution and controls label distribution divergence. To confirm the effectiveness of the proposed method, we first compare the algorithm with several baselines on some benchmarks and then test the algorithms under label space shift conditions. Empirical results demonstrate that the proposed method could outperform most baselines and achieve state-of-the-art performance, particularly showing the benefits under the label shift conditions.

We investigate upper bounds on the length of cost optimal plans that are valid for problems with 0-cost actions. We employ these upper bounds as horizons for a SAT-based encoding of planning with costs. Given an initial upper bound on the cost of the optimal plan, we experimentally show that this SAT-based approach is able to compute plans with better costs, and in many cases it can match the optimal cost. Also, in multiple instances, the approach is successful in proving that a certain cost is the optimal plan cost.

Throughout history, society has debated the morality of debt. In ancient times, debt--borrowing from another on the promise of repayment--was viewed in many cultures as sinful, with lending at interest especially repugnant. The concern that borrowers would become overindebted and enslaved to lenders meant that debts were routinely forgiven. These concerns continue to influence perceptions of lending and the regulation of credit markets today. Consider the prohibition against charging interest in Islamic finance and interest rate caps on payday lenders--companies that offer high-cost, short-term loans.

Konstantin Klemmer is a PhD student at the University of Warwick working at the intersection of machine learning and geographic data. He also serves as the Communications Chair for Climate Change AI. We talked about his research and the Climate Change AI organisation. Climate Change AI (CCAI) is a volunteer run organisation that catalyses impactful work at the intersection of climate change and machine learning by providing education and infrastructure, building a community, and advancing discourse. We also run a forum and regular community events like our fortnightly happy hour.

The extinction of large animals led to the human brain growing, a new study reveals. When humans first emerged in Africa 2.6 million years ago the average animal size was more than 1,000 pounds, making them easy prey. Throughout the Pleistocene era, creatures' sizes decreased by 90 percent, which forced our ancient ancestors to developing cunning and bold methods to capture their next meal. As they shifted to hunting small, swift prey animals, humans developed higher cognitive abilities and experienced a growth of brain volume from 650cc to 1,500cc. When humans first emerged in Africa 2.6 million years ago the average animal size was more than 1,000 pounds, making them easy prey Previous research shows that early humans survived by hunting large game, which provided them with the necessary fat and sources of energy to survive.

We propose an iterated version of Volunteer's Dilemma game through PRISM Model Checker (PRISM henceforth). This is useful because with this software, one can easily tune game parameters to get intuition of game dynamics. This can allow us to see what setting changes correlate with change in expected reward for each player. Additionally, PRISM can provide us a probabilistic graph that reflects a strategy that is optimal (or approximately optimal). Previous works [2] define public good game as a concurrent stochastic game, evaluating optimal strategies under a fixed set of parameters deciding the length of the game and the scaling factor associated with resource distribution.

Proximal Policy Optimization (PPO) is a popular on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent problems. In this work, we investigate Multi-Agent PPO (MAPPO), a multi-agent PPO variant which adopts a centralized value function. Using a 1-GPU desktop, we show that MAPPO achieves performance comparable to the state-of-the-art in three popular multi-agent testbeds: the Particle World environments, Starcraft II Micromanagement Tasks, and the Hanabi Challenge, with minimal hyperparameter tuning and without any domain-specific algorithmic modifications or architectures. In the majority of environments, we find that compared to off-policy baselines, MAPPO achieves better or comparable sample complexity as well as substantially faster running time. Finally, we present 5 factors most influential to MAPPO's practical performance with ablation studies.