Anton Nesterov | Applied ML
Posts Notebooks & Simulations About
  • Jul 24, 2026

    A Non-Linear Online Bandit for Set-Compatible Collection

    Machine LearningBanditsNon-Linear ModelsConcept Drift

    When an item's value depends on context, a linear value head is not a weak learner — it is a provably wrong one.

  • Jul 23, 2026

    Reflex Bandit: An Agent with Drift Detection for Active Exploitation Regimes

    Machine LearningBanditsConcept Drift

    An agent whose sensors are noiseless but whose meaning must be learned. When the world's shape drifts, ensemble disagreement is not enough — the agent has to watch its own prediction error. A tree-ensemble contextual bandit with two-timescale memory and an EWMA drift detector, in a regime where value-function RL is the wrong tool.

  • Jul 21, 2026

    MoB Queen: Mixture of Bandits with a Global Density Map and a Queen Move

    Machine LearningReinforcement LearningBandits

    A stateless agent with a noisy local sensor explores well by leaping — but on sparse worlds it circles in the half of the map it has already seen. The fix is a queen move: eight directional jumps aimed at the argmax of a predicted density map, scored by the same Q-function. The mixture is now three models, each winning in its own regime.

  • Jul 20, 2026

    Active Perception II: Adding a Visited Map to a GRU DRQN

    Reinforcement LearningDeep LearningPOMDPs

    The baseline GRU DRQN assumed its 48-unit hidden state could carry 'where the agent has already been' across a 400-cell grid. It could not. A 400-bit visited bitmap added as a third input tensor lifts the matched-pair ratio by 19%. The richer variant with three map channels lost the gain back — and that result is the load-bearing finding of this work.

  • Jul 19, 2026

    Active Perception I: A GRU DRQN for Discovery Under a Noisy Sensor

    Reinforcement LearningDeep LearningPOMDPs

    The moment the value of the next action depends on what was just done, you need recurrence. That is the entire argument for a GRU Deep Recurrent Q-Network: a learned memory of the recent trajectory, trained with the standard DQN stabilisers.

  • Jul 18, 2026

    Deep Q-Networks

    Reinforcement LearningDeep LearningQ-Learning

    DQN is the algorithm that taught a single neural network to beat human players across 49 Atari games from raw pixels. This is the preface: what Q-learning is, why a network breaks it, and the three tricks that put it back together.

  • Jul 18, 2026

    MoB: Mixture of Bandits for Sequential Exploring Problems with Stateless Agents and Limited Input

    Machine LearningReinforcement LearningBandits

    A stateless agent with a noisy local sensor is a blind, deaf, one-legged minesweeper — fine when the world is uniform, systematically wrong when the world is clustered. The fix is not a second expert, but a learned gate that knows when to disable the planner's long leap.

  • Jul 17, 2026

    The Sequential Recommender: Fitted Q-Iteration

    Machine LearningReinforcement LearningBandits

    The moment an action changes what the next decision can see or do, the bandit is myopic and the problem becomes sequential reinforcement learning.

  • Jul 14, 2026

    Building the Bandit Recommender

    Machine LearningBanditsReinforcement Learning

    The practical companion to the bandits essay. We state the recommendation problem the way a product team would, use the fishing simulator as a running analogy, dig into the hashing trick that makes the engine streamable, and compare ε-greedy against LinUCB on a real workload. With a brief survey of the rest of the bandit family.

  • Jul 12, 2026

    Contextual Bandits and Their Ethical Use Cases

    Machine LearningBanditsReinforcement Learning

    A contextual bandit is a machine-learning algorithm that makes billions of dollars a year and is roughly one-tenth as hyped as GPT. The TikTok doomscroll, the ad that follows you around for a week, the song Spotify queues next, Addictive Games — all of these are bandit-family algorithms.

  • Jun 21, 2026

    The Essence of Context Bandits

    banditstheory

    What a contextual bandit actually optimises, in one diagram and a handful of equations. With live math and a flow of the explore-exploit loop.

  • Jun 18, 2026

    Primer to Gradient Descent

    Machine LearningCalculusOptimization

    Gradient descent is the most used algorithm in machine learning, and the idea behind it is almost embarrassingly simple. This is the preface: without it, you won't understand 90% of ML.

  • Jun 17, 2026

    Quartiles, Ridge, and Lasso

    Machine LearningStatisticsRegression

    Three fundamentals that look unrelated but tell one story: how we describe data, and how we keep a model from believing it too much.

  • Jun 16, 2026

    Evaluation Metrics

    Machine LearningStatisticsEvaluation

    Five metrics, from R² to ROC/AUC, on interactive graphs.

© 2026 Anton A. Nesterov