Faster Teaching via POMDP Planning

Towards Principled Representation Learning from Videos for Reinforcement Learning

We study pre-training representations for decision-making using video data, which is abundantly available for tasks such as game agents and software testing. Even though significant empirical advances have been made on this problem, a theoretical understanding remains absent. We initiate the theoretical investigation into principled approaches for representation learning and focus on learning the latent state representations of the underlying MDP using video data. We study two types of settings: one where there is iid noise in the observation, and a more challenging setting where there is also the presence of exogenous noise, which is non-iid noise that is temporally correlated, such as the motion of people or cars in the background. We study three commonly used approaches: autoencoding, temporal contrastive learning, and forward modeling. We prove upper bounds for temporal contrastive learning and forward modeling in the presence of only iid noise. We show that these approaches can learn the latent state and use it to do efficient downstream RL with polynomial sample complexity. When exogenous noise is also present, we establish a lower bound result showing that the sample complexity of learning from video data can be exponentially worse than learning from action-labeled trajectory data. This partially explains why reinforcement learning with video pre-training is hard. We evaluate these representational learning methods in two visual domains, yielding results that are consistent with our theoretical findings.

Active Inference as Context Acquisition for AI Agents

Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed with a default assumption or spend tokens on a clarifying question, retrieval call, tool call, or prompt trial. We formulate this tradeoff as active inference for context acquisition. An inner inference step updates beliefs over a latent task state, and an outer decision selects the next context action, task action, or stop action to minimize expected free energy under cost. In deterministic settings, the epistemic term reduces to expected information gain, optionally normalized by token cost. We instantiate the framework in Optimal Question Asking (OQA), with exact posteriors and a dynamic programming oracle, and benchmark frontier language models on binary and multiway categorical tasks from 25 to 300 candidates. We also study clarification before generation and automated prompt optimization under token budgets. The formulation is model-agnostic and views active inference as a design principle for the context-acquisition layer of AI agents.

Curriculum learning

Humans and animals learn much better when the examples are not randomly presented but organized in a meaningful order which illustrates gradually more concepts, and gradually more complex ones. Here, we formalize such training strategies in the context of machine learning, and call them "curriculum learning". In the context of recent research studying the difficulty of training in the presence of non-convex training criteria (for deep deterministic and stochastic neural networks), we explore curriculum learning in various set-ups. The experiments show that significant improvements in generalization can be achieved. We hypothesize that curriculum learning has both an effect on the speed of convergence of the training process to a minimum and, in the case of non-convex criteria, on the quality of the local minima obtained: curriculum learning can be seen as a particular form of continuation method (a general strategy for global optimization of non-convex functions).

Unifying Principles of Generalization: Past, Present, and Future

Generalization, defined as applying limited experiences to novel situations, represents a cornerstone of human intelligence. Our review traces the evolution and continuity of psychological theories of generalization, from its origins in concept learning (categorizing stimuli) and function learning (learning continuous input-output relationships) to domains such as reinforcement learning and latent structure learning. Historically, there have been fierce debates between approaches based on rule-based mechanisms, which rely on explicit hypotheses about environmental structure, and approaches based on similarity-based mechanisms, which leverage comparisons to prior instances. Each approach has unique advantages: Rules support rapid knowledge transfer, while similarity is computationally simple and flexible. Today, these debates have culminated in the development of hybrid models grounded in Bayesian principles, effectively marrying the precision of rules with the flexibility of similarity. The ongoing success of hybrid models not only bridges past dichotomies but also underscores the importance of integrating both rules and similarity for a comprehensive understanding of human generalization.

Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction

Predicting item difficulty is a central challenge in educational assessment, where accurate estimates are critical for fairness and effective test construction. Existing methods are either expensive to scale or limited in predictive power, even with recent Large Language Model(LLM) related methods. Meanwhile, Large Reasoning Models (LRMs) expose detailed reasoning traces that resemble human problem solving, creating new opportunities for difficulty modeling. We propose a new perspective that treats item difficulty as an observable consequence of problem-solving burden. Building on this formulation, we introduce a structured framework that converts LRM reasoning traces into sentence-level episode sequences using a cognitively grounded taxonomy and then derives compact process features for downstream prediction, which is named Epi2Diff (Episode to Difficulty). This produces a structured process-based representation of each assessment item. Across four real-world human difficulty datasets, our method consistently outperforms various methods, including fine-tuning small encoder-only language models, LLM In-Context Learning, and LLM Supervised Finetuning with full parameters or LoRA. Epi2Diff delivers an 8.0% relative gain in classification and a 24.4% reduction in RMSE for regression against strong baselines. We also find that harder items are associated with more effortful and iterative reasoning dynamics. Moreover, our method not only predicts the difficulty value, but it also provides a new perspective on the explanation of the predicted difficulty based on the episode transition of LRM responses. These results suggest that structured reasoning dynamics are both predictive and interpretable, and provide a new lens for understanding the utility of LRMs in educational measurement.

The Wisdom of Individuals: Exploring People's Knowledge About Everyday Events Using Iterated Learning

Abstract Determining the knowledge that guides human judgments is fundamental to understanding how people reason, make decisions, and form predictions. We use an experimental procedure called ‘‘iterated learning,’’ in which the responses that people give on one trial are used to generate the data they see on the next, to pinpoint the knowledge that informs people's predictions about everyday events (e.g., predicting the total box office gross of a movie from its current take). In particular, we use this method to discriminate between two models of human judgments: a simple Bayesian model ( Griffiths & Tenenbaum, 2006 ) and a recently proposed alternative model that assumes people store only a few instances of each type of event in memory (Min K ; Mozer, Pashler, & Homaei, 2008 ). Although testing these models using standard experimental procedures is difficult due to differences in the number of free parameters and the need to make assumptions about the knowledge of individual learners, we show that the two models make very different predictions about the outcome of iterated learning. The results of an experiment using this methodology provide a rich picture of how much people know about the distributions of everyday quantities, and they are inconsistent with the predictions of the Min K model. The results suggest that accurate predictions about everyday events reflect relatively sophisticated knowledge on the part of individuals.

Language and Experience: A Computational Model of Social Learning in Complex Tasks

The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI systems? We present a computational framework that models social learning as joint probabilistic inference over structured, executable world models given sensorimotor and linguistic data. We make this possible by turning a pretrained language model into a probabilistic model of how humans share advice conditioned on their beliefs, allowing our agents both to generate advice for others and to interpret linguistic input as evidence during Bayesian inference. Using behavioral experiments and simulations across 10 video games, we show how linguistic guidance can shape exploration and accelerate learning by reducing risky interactions and speeding up key discoveries in both humans and models. We further explore how knowledge can accumulate across generations through iterated learning experiments and demonstrate successful knowledge transfer between humans and models -- revealing how structured, language-compatible representations might enable human-machine collaborative learning.

A Comprehensive Survey of Continual Learning: Theory, Method and Application

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to develop themselves adaptively. In a general sense, continual learning is explicitly limited by catastrophic forgetting, where learning a new task usually results in a dramatic performance degradation of the old tasks. Beyond this, increasingly numerous advances have emerged in recent years that largely extend the understanding and application of continual learning. The growing and widespread interest in this direction demonstrates its realistic significance as well as complexity. In this work, we present a comprehensive survey of continual learning, seeking to bridge the basic settings, theoretical foundations, representative methods, and practical applications. Based on existing theoretical and empirical results, we summarize the general objectives of continual learning as ensuring a proper stability-plasticity trade-off and an adequate intra/inter-task generalizability in the context of resource efficiency. Then we provide a state-of-the-art and elaborated taxonomy, extensively analyzing how representative methods address continual learning, and how they are adapted to particular challenges in realistic applications. Through an in-depth discussion of promising directions, we believe that such a holistic perspective can greatly facilitate subsequent exploration in this field and beyond.

#Exploration: A Study of Count-Based Exploration for Deep...

Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision...

Factored Latent Action World Models

Learning latent actions from action-free video has emerged as a powerful paradigm for scaling up controllable world model learning. Latent actions provide a natural interface for users to...

Look-ahead Reasoning with a Learned Model in Imperfect Information Games

Test-time reasoning significantly enhances pre-trained AI agents' performance. However, it requires an explicit environment model, often unavailable or overly complex in real-world scenarios....

Letta

The agent that remembers and learns

Letta

Making machines that learn. Create stateful agents that remember everything, learn continuously, and improve themselves over time.

Bridging the human–AI knowledge gap through concept discovery and transfer in AlphaZero

AI systems have attained superhuman performance across various domains. If the hidden knowledge encoded in these highly capable systems can be leveraged, human knowledge and performance can be advanced. Yet, this internal knowledge is difficult to extract. Due to the vast space of possible internal representations, searching for meaningful new conceptual knowledge can be like finding a needle in a haystack. Here, we introduce a method that extracts new chess concepts from AlphaZero, an AI system that mastered chess via self-play without human supervision. Our method excavates vectors that represent concepts from AlphaZero’s internal representations using convex optimization, and filters the concepts based on teachability (whether the concept is transferable to another AI agent) and novelty (whether the concept contains information not present in human chess games). These steps ensure that the discovered concepts are useful and meaningful. For the resulting set of concepts, prototypes (chess puzzle–solution pairs) are presented to experts for final validation. In a preliminary human study, four top chess grandmasters (all former or current world chess champions) were evaluated on their ability to solve concept prototype positions. All grandmasters showed improvement after the learning phase, suggesting that the concepts are at the frontier of human understanding. Despite the small scale, our result is a proof of concept demonstrating the possibility of leveraging knowledge from a highly capable AI system to advance the frontier of human knowledge; a development that could bear profound implications and shape how we interact with AI systems across many applications.

Reinforcement Learning from Human Feedback

The authoritative guide for Reinforcement learning from human feedback, alignment, and post-training LLMs. Aligning AI models to human preferences helps them become safer, smarter, easier to use, and tuned to the exact style the creator desires. Reinforcement Learning From Human Feedback (RHLF) is the process for using human responses to a model’s output to shape its alignment, and therefore its behavior. In Reinforcement Learning from Human Feedback, author Nathan Lambert blends diverse perspectives from fields like philosophy and economics with the core mathematics and computer science of RLHF to provide a practical guide you can use to apply RLHF to your models. In Reinforcement Learning from Human Feedback you’ll discover: How today’s most advanced AI models are taught from human feedback How large-scale preference data is collected and how to improve your data pipelines A comprehensive overview with derivations and implementations for the core policy-gradient methods used to train AI models with reinforcement learning (RL) Direct Preference Optimization (DPO), direct alignment algorithms, and simpler methods for preference finetuning How RLHF methods led to the current reinforcement learning from verifiable rewards (RLVR) renaissance Tricks used in industry to round out models, from product, character or personality training, AI feedback, and more How to approach evaluation and how evaluation has changed over the years Standard recipes for post-training combining more methods like instruction tuning with RLHF Behind-the-scenes stories from building open models like Llama-Instruct, Zephyr, Olmo, and Tülu After ChatGPT used RLHF to become production-ready, this foundational technique exploded in popularity. In Reinforcement Learning from Human Feedback, AI expert Nathan Lambert gives a true industry insider's perspective on modern RLHF training pipelines, and their trade-offs. Using hands-on experiments and mini-implementations, Nathan clearly and concisely introduces the alignment techniques that can transform a generic base model into a human-friendly tool.

Query by committee

We propose an algorithm called query by commitee, in which a committee of students is trained on the same data set. The next query is chosen according to the principle of maximal disagreement. The algorithm is studied for two toy models: the high-low game and perceptron learning of another perceptron. As the number of queries goes to infinity, the committee algorithm yields asymptotically finite information gain. This leads to generalization error that decreases exponentially with the number of examples. This in marked contrast to learning from randomly chosen inputs, for which the information gain approaches zero and the generalization error decreases with a relatively slow inverse power law. We suggest that asymptotically finite information gain may be an important characteristic of good query algorithms.