Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Field notes

2,343 notes from my AI research vault, mapped by topic. Pick a topic to see its notes, or search.

Every note is in the list below. The web of topics draws here once the page has loaded.

128 of 2,343 notes match.

  • Question answered
  • Source note
  • Topic
  • Shared notes

Notes on reinforcement learning

128 notes, page 4 of 6

  1. When Synthetic Speech Is All You Have: Better Call GRPO

    Source note · Jul 9, 2026 · reinforcement learning, privacy

    The paper presents a new approach for adapting Large Language Model (LLM) based Automatic Speech Recognition (ASR) systems to regulated domains like banking using synthetic text-to-speech instead of real speech due to…

  2. When Synthetic Speech Is All You Have: Better Call GRPO

    Source note · Jul 9, 2026 · ai, reinforcement learning, speech recognition

    Researchers present a method called Group Relative Policy Optimization (GRPO) that improves the accuracy of synthetic speech-to-text conversion compared to traditional methods. This could be particularly useful in…

  3. Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning

    Source note · Jul 8, 2026 · ai, reinforcement learning, grading

    The paper introduces Agon, a new reinforcement learning approach that trains two reasoning models by having them compete against each other. This competitive grading system aims to improve the quality of thinking…

  4. Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning

    Source note · Jul 8, 2026 · reinforcement learning

    The paper introduces a new method called Agon for reinforcement learning that allows two competing models to grade each other's reasoning during training. This approach aims to improve the quality of solutions by…

  5. Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26

    Source note · Jul 8, 2026 · artificial intelligence, reinforcement learning

    The researchers present Reward-Adaptive Iterative Discovery (RAID), a new approach for automated game testing in the gaming industry, specifically focusing on the ice hockey game EA SPORTS NHL 26. The goal is to reduce…

  6. RLVP: Penalize the Path, Reward the Outcome

    Source note · Jul 8, 2026 · artificial intelligence, machine learning, reinforcement learning

    The paper 'RLVP: Penalize the Path, Reward the Outcome' by Bojie Li and Noah Shi proposes a method for training artificial agents to perform tasks effectively in real-world environments. This method addresses two main…

  7. RLVP: Penalize the Path, Reward the Outcome

    Source note · Jul 8, 2026 · reinforcement learning

    The paper 'RLVP: Penalize the Path, Reward the Outcome' discusses challenges faced by agents learning from real-world interactions and proposes a solution to improve their performance and adherence to constraints. The…

  8. Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

    Source note · Jul 8, 2026 · ai, large language models, reinforcement learning

    The paper proposes a new method called Single-rollout Asynchronous Optimization (SAO) for Reinforcement Learning (RL) in post-training large language models (LLMs). SAO aims to improve stability and task effectiveness…

  9. Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

    Source note · Jul 8, 2026 · large language models, reinforcement learning

    The paper introduces Single-rollout Asynchronous Optimization (SAO), a new approach to reinforcement learning (RL) aimed at post-training large language models (LLMs). SAO addresses stability and off-policy challenges…

  10. Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

    Source note · Jul 8, 2026 · large language models, reinforcement learning

    In this paper, the authors introduce Single-rollout Asynchronous Optimization (SAO), a new approach to reinforcement learning (RL) for post-training large language models (LLMs). SAO aims to improve training stability…

  11. Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design

    Source note · Jul 7, 2026 · large language models, reinforcement learning

    Researchers have improved the quality of process models generated by large language models (LLMs) using reinforcement learning (RL). They found that designing the reward function is crucial for optimizing beyond the…

  12. Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents

    Source note · Jul 7, 2026 · reinforcement learning, large language model, policy optimization

    The paper proposes a new method called Information Gain-based Rollout Policy Optimization (IGRPO) for improving large language model (LLM) agents in long-horizon search tasks. The method addresses the issue of existing…

  13. Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents

    Source note · Jul 7, 2026 · artificial intelligence, large language models, reinforcement learning

    The paper presents Information Gain-based Rollout Policy Optimization (IGRPO), a new framework for improving large language model agents in long-horizon search tasks. IGRPO aims to allocate rollout budget more…

  14. Multi-Agent Deep Reinforcement Learning for Multi Objective Battery Management in Dairy Farms

    Source note · Jul 7, 2026 · reinforcement learning, deep learning

    This research introduces a multi-objective optimization control system for battery management in dairy farms that utilizes differential evolution and multi-agent deep reinforcement learning. The system aims to improve…

  15. Adaptive Inference Batching using Policy Gradients

    Source note · Jul 6, 2026 · reinforcement learning

    The paper investigates using reinforcement learning (RL) to create adaptive batching and routing policies for inference serving systems that can handle bursty, heterogeneous workloads. The research finds that in…

  16. LLM-as-a-Verifier: A General-Purpose Verification Framework

    Source note · Jul 6, 2026 · ai, machine learning, reinforcement learning

    In this research, a general-purpose verification framework called LLM-as-a-Verifier is introduced. This framework provides detailed feedback for agentic tasks without requiring additional training. The framework…

  17. Relational Multi-Agent Reinforcement Learning for Dynamic Pricing in High-Speed Railway Markets

    Source note · Jul 6, 2026 · reinforcement learning, graph theory

    Researchers propose a new approach for dynamic pricing in liberalized railway systems using Relational Multi-Agent Reinforcement Learning (RL). The method models the environment as a graph, process features of entities…

  18. TREK: Distill to Explore, Reinforce to Refine

    Source note · Jul 6, 2026 · ai, reinforcement learning, optimization

    The paper proposes a method called TREK (Teacher-Routed Exploration via Forward KL) to improve Group Relative Policy Optimization (GRPO). TREK uses distillation for exploration support expansion and can work with…

  19. Weak-to-Strong Generalization via Direct On-Policy Distillation

    Source note · Jul 6, 2026 · reinforcement learning, language model

    Researchers propose a method called Direct On-Policy Distillation (Direct-OPD) for improving stronger language models by leveraging the knowledge gained from reinforcement learning on smaller, weaker models. This…

  20. EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

    Source note · Jul 2, 2026 · ai, machine learning, evaluation

    A new evaluation setting called Autonomous Policy Evolution (APE) is introduced in a benchmark named EvoPolicyGym, which is used to test how autonomous agents iteratively improve their policy systems within a fixed…

  21. EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

    Source note · Jul 2, 2026 · ai, machine learning, reinforcement learning

    In the research paper titled 'EvoPolicyGym', the authors introduce a controlled evaluation setting called Autonomous Policy Evolution (APE) for assessing how autonomous agents iteratively improve their executable…

  22. WorldSample: Closed-loop Real-robot RL with World Modelling

    Source note · Jul 2, 2026 · reinforcement learning, robotics

    The paper presents WorldSample, a framework that uses reinforcement learning (RL) to improve the performance of robots by creating synthetic transitions based on real rollouts and a post-trained world model. This…

  23. Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm

    Source note · Jul 1, 2026 · reinforcement learning

    Researchers have proposed a new method called Generative Meta-Learning with Human Feedback (GMHF) to improve the performance of machine learning models in environments different from their training distribution…

  24. Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

    Source note · Jun 30, 2026 · reinforcement learning, healthcare, ai in medicine

    The paper introduces Medical Reasoning-aware Policy Optimization (MRPO), a reinforcement learning algorithm for medical multimodal reasoning, which aims to optimize the reasoning process and reduce cascading errors…

An AI research agent drafts these notes from public papers and posts, and each one keeps its source link. Only the folders I choose to publish leave my Obsidian vault.