Hessian Center for Artificial Intelligence (Hessian.ai), This paper introduces a new imitation learning framework based on energy-based generative models capable of learning complex, physics-dependent, robot motion policies through state-only expert motion trajectories. Our algorithm, called Noise-conditioned Energy-based Annealed Rewards (NEAR), constructs several perturbed versions of the expert's motion data distribution and learns smooth, and well-defined representations of the data distribution's energy function using denoising score matching. We propose to use these learnt energy functions as reward functions to learn imitation policies via reinforcement learning. We also present a strategy to gradually switch between the learnt energy functions, ensuring that the learnt rewards are always well-defined in the manifold of policy-generated samples. We evaluate our algorithm on complex humanoid tasks such as locomotion and martial arts and compare it with state-only adversarial imitation learning algorithms like Adversarial Motion Priors (AMP). Our framework sidesteps the optimisation challenges of adversarial imitation learning techniques and produces results comparable to AMP in several quantitative metrics across multiple imitation settings. Learning skills through imitation is probably the most cardinal form of learning for human beings. Whether it is a child learning to tie their shoelaces, a dancer learning a new pose, or a gymnast learning a fast and complex manoeuvre, acquiring new motor skills for humans typically involves guidance from another skilled human in the form of demonstrations. Acquiring skills from these demonstrations typically boils down to interpreting the individual features of the demonstration motion - for example, the relative positions of the limbs in a dance pose - and subsequently attempting to recreate the same features via repeated trial and error. Imitation learning (IL) is an algorithmic interpretation of this simple strategy of learning skills by matching the features of one's own motions with the features of the expert's demonstrations. Such a problem can be solved by various means, with techniques like behavioural cloning (BC), inverse reinforcement learning (IRL), and their variants being popular choices (Osa et al., 2018). The imitation learning problem can also be formulated in various subtly differing ways, leading to different constraints on the types of algorithms that solve the problem.

Large language models (LLMs) achieve remarkable performance on challenging benchmarks that are often structured as multiple-choice question-answering (QA) tasks. Zero-shot Chain-of-Thought (CoT) prompting enhances reasoning in LLMs but provides only vague and generic guidance ("think step by step"). This paper introduces ARR, an intuitive and effective zero-shot prompting method that explicitly incorporates three key steps in QA solving: analyzing the intent of the question, retrieving relevant information, and reasoning step by step. Comprehensive experiments across diverse and challenging QA tasks demonstrate that ARR consistently improves the Baseline (without ARR prompting) and outperforms CoT. Ablation and case studies further validate the positive contributions of each component: analyzing, retrieving, and reasoning. Notably, intent analysis plays a vital role in ARR. Additionally, extensive evaluations across various model sizes, LLM series, and generation settings solidify the effectiveness, robustness, and generalizability of ARR.

The advent of transformer-based large language models (LLMs) has reignited the philosophical debate of human significance - a question that has persisted for millennia. Aristotle thought the function of humans was to live according to the rational principle, which was something that distinguished us from other animals (Aristotle, 2014) . Back then, this might have seemed like a reasonable conclusion, as humans use complex language and abstract thinking to a degree that other animals simply do not. However, recent advancements in artificial intelligence (AI) are shining light on the possibility that in the future we might be living in a world in which our creation is more intelligent than us - or perhaps that this world is already here. In many benchmarks comparing humans and AI, LLMs have shown a trend of rapid increase in performance. In SimpleBench, which measures common sense reasoning and social intelligence, GPT-4o scored only 17.8% and o1-preview 41.7% (Philip & Hemang, 2024) .

We develop an algorithm to semantically parse linear ordering problems, which require a model to arrange entities using deductive reasoning. Our method takes as input a number of premises and candidate statements, parsing them to a first-order logic of an ordering domain, and then utilizes constraint logic programming to infer the truth of proposed statements about the ordering. Our semantic parser transforms Heim and Kratzer's syntax-based compositional formal semantic rules to a computational algorithm. This transformation involves introducing abstract types and templates based on their rules, and introduces a dynamic component to interpret entities within a contextual framework. Our symbolic system, the Formal Semantic Logic Inferer (FSLI), is applied to answer multiple choice questions in BIG-bench's logical_deduction multiple choice problems, achieving perfect accuracy, compared to 67.06% for the best-performing LLM (GPT-4) and 87.63% for the hybrid system Logic-LM. These promising results demonstrate the benefit of developing a semantic parsing algorithm driven by first-order logic constructs.

I have read the authors' response and other reviewers' comments. I choose to raise my score. The way these points are utilized is also inspirational. Cons: - Like many other work in nonlinear dimension reduction, this paper does not provide a systematic, convincing way to evaluate and compare the new approach against previous methods which are claimed to be less effective. The visual comparison in Figure 6 appears cherry-picking in methodology.

Dimensionality reduction such as tSNE is widely used to visualize and interpret (and often over interpret) high-dimensional data. Thus such visualization has become a staple in the field and it is has been a while since I have seen substantial progress in improving such visualization techniques and this paper is such a case. Reviewer 1 summarizes the contribution and its importance better than I could word it myself: This work has two main contributions, which are sufficiently significant given the interest in visualization and dimensionality reduction via SNE, tSNE, and further extensions: 1. Identification of pressure points that are "stuck" in suboptimal location in the embedding due to local minima caused by dimensionality constraints. The manuscript is well written, well motivated, and convincingly establishes the reasoning behind the proposed approach as well as its effectiveness. All three reviewers agree on accepting the paper. All reviewers agreed that the paper provided new insights, a novel approach, a valuable practical contribution which is extensively validated on multiple datasets and is well written.

The move from hand-designed features to learned features in machine learning has been wildly successful. In spite of this, optimization algorithms are still designed by hand. In this paper we show how the design of an optimization algorithm can be cast as a learning problem, allowing the algorithm to learn to exploit structure in the problems of interest in an automatic way. Our learned algorithms, implemented by LSTMs, outperform generic, hand-designed competitors on the tasks for which they are trained, and also generalize well to new tasks with similar structure. We demonstrate this on a number of tasks, including simple convex problems, training neural networks, and styling images with neural art.

The goal of minimizing misclassification error on a training set is often just one of several real-world goals that might be defined on different datasets. For example, one may require a classifier to also make positive predictions at some specified rate for some subpopulation (fairness), or to achieve a specified empirical recall. Other real-world goals include reducing churn with respect to a previously deployed model, or stabilizing online training. In this paper we propose handling multiple goals on multiple datasets by training with dataset constraints, using the ramp penalty to accurately quantify costs, and present an efficient algorithm to approximately optimize the resulting non-convex constrained optimization problem. Experiments on both benchmark and real-world industry datasets demonstrate the effectiveness of our approach.

We investigate a reduction of supervised learning to game playing that reveals new connections and learning methods. For convex one-layer problems, we demonstrate an equivalence between global minimizers of the training problem and Nash equilibria in a simple game. We then show how the game can be extended to general acyclic neural networks with differentiable convex gates, establishing a bijection between the Nash equilibria and critical (or KKT) points of the deep learning problem. Based on these connections we investigate alternative learning methods, and find that regret matching can achieve competitive training performance while producing sparser models than current deep learning approaches.

We introduce the Adaptive Skills, Adaptive Partitions (ASAP) framework that (1) learns skills (i.e., temporally extended actions or options) as well as (2) where to apply them. We believe that both (1) and (2) are necessary for a truly general skill learning framework, which is a key building block needed to scale up to lifelong learning agents. The ASAP framework is also able to solve related new tasks simply by adapting where it applies its existing learned skills. We prove that ASAP converges to a local optimum under natural conditions. Finally, our experimental results, which include a RoboCup domain, demonstrate the ability of ASAP to learn where to reuse skills as well as solve multiple tasks with considerably less experience than solving each task from scratch.