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 2 of 6

  1. Contextual Information Policy Optimization for Search Agents

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

    The researchers propose a new reinforcement learning framework called Contextual Information Policy Optimization (CIPO) to improve the reliability of search agents for knowledge-intensive tasks. CIPO encourages the use…

  2. Contextual Information Policy Optimization for Search Agents

    Source note · Aug 6, 2026 · reinforcement learning, policy optimization

    The paper proposes a new method called Contextual Information Policy Optimization (CIPO) to improve the reliability of search agents for complex or evolving information tasks. CIPO aligns policy optimization with…

  3. EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning

    Source note · Aug 6, 2026 · ai, reinforcement learning, language model

    Researchers have developed EnvACE, a method for training large language model agents that simulates environment interactions during training using world rehearsal instead of relying on real or synthesized executable…

  4. EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning

    Source note · Aug 6, 2026 · ai, reinforcement learning

    The researchers introduce EnvACE, a method for reinforcement learning that replaces external environment interactions during training with world rehearsal. This method allows the policy to internalize the relationship…

  5. EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning

    Source note · Aug 6, 2026 · ai, reinforcement learning

    Researchers have introduced EnvACE, a method for training large language model agents using world rehearsal instead of interactions with real or simulated environments. The method involves the policy alternating…

  6. EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning

    Source note · Aug 6, 2026 · large language models, reinforcement learning

    The paper introduces EnvACE, a method for training large language model agents for long-term tool use without relying on interactions with real or synthesized environments, which can be costly to construct and verify…

  7. iARCS: Iterative Agentic RL for Controllable 3D Scene Generation

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

    The paper presents iARCS, an iterative agentic reinforcement learning framework for enhancing the performance of synthetic 3D scene generators by adapting them to meet task-specific functional constraints, such as…

  8. Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation

    Source note · Aug 5, 2026 · ai, machine learning, reinforcement learning

    Researchers propose Observation-Calibrated Self-Distillation (OCSD) to address a confounding issue in On-Policy Self-Distillation (OPSD), a method used to train large language model agents. OCSD aims to attribute…

  9. Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation

    Source note · Aug 5, 2026 · large language models, reinforcement learning, self-distillation

    Researchers propose a new method called Observation-Calibrated Self-Distillation (OCSD) to train large language models in reinforcement learning. OCSD addresses a confounding issue in previous methods by comparing two…

  10. TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning

    Source note · Aug 4, 2026 · reinforcement learning, self-distillation

    The authors propose a framework called TurnSight for Tool-Integrated Reasoning (TIR). This framework aims to improve fine-grained credit assignment in long-horizon TIR scenarios by addressing the limitations of…

  11. On-Policy and Off-Policy Learning for Large Action Spaces

    Source note · Jul 30, 2026 · reinforcement learning, optimization, policy learning

    The paper discusses policy learning in interactive systems with large action spaces, where agents observe contexts, select actions, and receive partial feedback. The research focuses on two paradigms: on-policy…

  12. OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

    Source note · Jul 30, 2026 · evaluation, reinforcement learning, vision-language models

    The research introduces OSReward, a new benchmark for evaluating the reliability of vision-language models (VLMs) used to judge computer-using agents' trajectories. The study finds that state-of-the-art VLMs have a…

  13. Graph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability Detection

    Source note · Jul 29, 2026 · reinforcement learning

    Researchers propose VulAgentRL, a framework for interprocedural vulnerability detection using agentic reinforcement learning (RL) and a Code Property Graph (CPG). The CPG verifies the evidence cited by the policy…

  14. SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

    Source note · Jul 29, 2026 · artificial intelligence, machine learning, reinforcement learning

    SkillRise is a new reinforcement learning framework that helps large language model agents solve related yet distinct tasks more efficiently. It organizes tasks into sequences and uses a single policy to alternate…

  15. Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections

    Source note · Jul 23, 2026 · reinforcement learning, deep learning, autonomous vehicles

    A new approach called Master-Agent Proto-plan System (MAPS) is proposed to improve the coordination of autonomous vehicles at unsignalized intersections. MAPS uses a hierarchical deep reinforcement learning…

  16. Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections

    Source note · Jul 23, 2026 · reinforcement learning, multi-agent systems, autonomous vehicles

    The paper introduces a new deep reinforcement learning architecture called Master-Agent Proto-plan System (MAPS) for coordinating autonomous vehicles at unsignalized intersections. The MAPS system uses a centralized…

  17. Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections

    Source note · Jul 23, 2026 · reinforcement learning, multi-agent systems, deep learning

    Researchers present MAPS, a deep reinforcement learning architecture for coordinating autonomous vehicles at unsignalized intersections. The system uses a central Master agent that generates a global coordination…

  18. Expert Behavior Prior Reinforcement Learning

    Source note · Jul 23, 2026 · reinforcement learning

    The paper proposes a new method called Expert Behavior Prior (EBP) for behavior prior reinforcement learning (BPRL). EBP aims to improve the effectiveness of policy priors by generating expert policy priors directly…

  19. MIRROR: Learning from the Other View for Multi-Modal Reasoning

    Source note · Jul 23, 2026 · large language models, reinforcement learning, vision-language models

    Researchers have created a new approach called Modality-Informed Reciprocal Reasoning Optimization (MIRROR) to improve the reasoning abilities of both large language models and vision-language models. The approach uses…

  20. PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning

    Source note · Jul 23, 2026 · ai, reinforcement learning, policy optimization

    The authors propose a new training paradigm called PATS for reinforcement learning agents that learn long-term tasks. PATS converts rollout groups from the latest policy into evidence cards and adjusts the context used…

  21. PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning

    Source note · Jul 23, 2026 · reinforcement learning, policy optimization

    The paper 'PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning' proposes a new training paradigm called Pats, which aims to improve the performance of long-horizon reinforcement learning agents…

  22. PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning

    Source note · Jul 23, 2026 · reinforcement learning

    Researchers propose a new method called PATS for training agents in long-term reinforcement learning tasks. The method uses a dynamic training scaffold that adapts to the evolving policy, providing concrete guidance to…

  23. Generalized Kalman filter based temporal difference reinforcement learning

    Source note · Jul 22, 2026 · reinforcement learning, uncertainty quantification

    The paper introduces a new reinforcement learning framework that combines conditional expectation theory with a generalized Kalman filter. This approach allows for the estimation of both the value function and its…

  24. Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning

    Source note · Jul 22, 2026 · reinforcement learning, robotics

    The paper describes a new control stack for miniature humanoids that allows a single operator to see, manipulate, and navigate in distant environments using Virtual Reality (VR) for upper-body teleoperation and…

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.