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 5 of 6

  1. GR2 Technical Report

    Source note · Jun 30, 2026 · machine learning, large language models, reinforcement learning

    Researchers present GR2 (Generative Reasoning Re-Ranker), a framework designed to improve the performance of recommendation systems in an industrial setting. The system combines mid-training on semantic IDs…

  2. QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

    Source note · Jun 30, 2026 · reinforcement learning, evaluation methods

    The paper introduces QVal, a training-free testbed for evaluating dense supervision signals in long-horizon reinforcement learning tasks. QVal measures the alignment of a method's score with the Q-values of a strong…

  3. Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

    Source note · Jun 30, 2026 · ai, machine learning, reinforcement learning

    Researchers have developed two new mechanisms - Reinforcement Learning with Metacognitive Feedback (RLMF) and Metacognitive Data Selection - to improve the performance of Language Models (LLMs). The goal is to make…

  4. Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

    Source note · Jun 30, 2026 · reinforcement learning

    The paper discusses a new approach called Reinforcement Learning with Metacognitive Feedback (RLMF) to improve Language Model's (LLM) metacognitive abilities. The RLMF aims to help LLMs better monitor and regulate…

  5. TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning

    Source note · Jun 30, 2026 · reinforcement learning, credit assignment

    The paper proposes a new framework called TRIAGE for credit assignment in agentic reinforcement learning. This framework adds a semantic role axis to outcome credit, allowing for more accurate reward distribution for…

  6. Automating Potential-based Reward Shaping with Vision Language Model Guidance

    Source note · Jun 25, 2026 · reinforcement learning, automation, vision-language models

    Researchers introduce a new method called VLM-PBRS for automating potential-based reward shaping using vision language model (VLM) feedback. The aim is to improve reinforcement learning agents' ability to learn from…

  7. Automating Potential-based Reward Shaping with Vision Language Model Guidance

    Source note · Jun 25, 2026 · reinforcement learning, robotics, vision-language models

    Researchers have developed a new method called VLM-PBRS for automating potential-based reward shaping in reinforcement learning agents. This method uses vision language models (VLMs) to learn the potential function…

  8. Automating Potential-based Reward Shaping with Vision Language Model Guidance

    Source note · Jun 25, 2026 · reinforcement learning, vision language model, potential-based reward shaping

    In this research, the authors present a new framework called VLM-guided PBRS, which learns potential functions for reward shaping directly from vision language model (VLM) feedback. The goal is to address the…

  9. Automating Potential-based Reward Shaping with Vision Language Model Guidance

    Source note · Jun 25, 2026 · reinforcement learning, robotics, vision-language models

    Researchers have developed a new method for reinforcement learning agents using vision language models (VLMs). The approach called VLM-guided PBRS learns a potential function from VLM feedback to address the challenge…

  10. Joint Learning of Experiential Rules and Policies for Large Language Model Agents

    Source note · Jun 25, 2026 · ai, machine learning, reinforcement learning

    The paper introduces a new method called Joint Learning of Experiential Rules and Policies (JERP) for large language model agents operating in multi-step interactive environments. The main challenge addressed is…

  11. Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)

    Source note · Jun 25, 2026 · reinforcement learning, simulation

    The text describes a prize-winning system for bimanual garment folding from the LeHome Challenge 2026. The system used a reinforcement learning loop to improve a vision-language-action (VLA) policy, placing first in…

  12. Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)

    Source note · Jun 25, 2026 · reinforcement learning

    A research paper describes a system that won first place online and second place offline in the LeHome Challenge 2026, a competition on bimanual garment folding. The system improves a vision-language-action (VLA)…

  13. State Representation Matters in Deep Reinforcement Learning: Application to Energy Trading

    Source note · Jun 25, 2026 · reinforcement learning

    Researchers studied how the representation of a state given to a reinforcement learning (RL) agent impacts energy trading decisions. They used a fixed Double DQN agent in a pumped-storage arbitrage environment and…

  14. State Representation Matters in Deep Reinforcement Learning: Application to Energy Trading

    Source note · Jun 25, 2026 · artificial intelligence, reinforcement learning, energy

    Researchers studied the impact of state representation in deep reinforcement learning (DRL) for energy trading decisions, using a fixed Double DQN agent in the HydroDam environment. They found that combining absolute…

  15. State Representation Matters in Deep Reinforcement Learning: Application to Energy Trading

    Source note · Jun 25, 2026 · reinforcement learning, energy

    Researchers compared different methods for representing market conditions in reinforcement learning (RL) models for energy trading. They found that combining multiple types of features led to stronger performance…

  16. FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation

    Source note · Jun 24, 2026 · artificial intelligence, reinforcement learning, vla models

    The paper introduces FORCE, a framework designed to improve the efficiency of reinforcement learning fine-tuning for Vision-Language-Action (VLA) models. The framework consists of three stages: Value-Calibrated…

  17. FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation

    Source note · Jun 24, 2026 · machine learning, reinforcement learning, vla models

    The research introduces FORCE, a three-stage framework for fine-tuning Vision-Language-Action (VLA) models using Reinforcement Learning (RL). The framework addresses sample inefficiency issues by implementing a…

  18. Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization

    Source note · Jun 24, 2026 · reinforcement learning, deep learning, quantization

    The authors present HiReLC, a framework that uses reinforcement learning to automatically compress deep neural networks by pruning and quantizing them. The framework works in two levels: low-level agents (LLAs)…

  19. Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization

    Source note · Jun 24, 2026 · reinforcement learning, quantization, active learning

    The paper presents HiReLC, a framework that uses reinforcement learning to compress deep neural networks by pruning and quantizing them. The framework divides the compression search into two levels: low-level agents…

  20. Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization

    Source note · Jun 24, 2026 · reinforcement learning, quantization, active learning

    The paper introduces HiReLC, a hierarchical reinforcement learning framework that automates the joint quantization and structured pruning of deep neural networks. It operates at two levels: low-level agents (LLAs)…

  21. Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound

    Source note · Jun 24, 2026 · reinforcement learning, multi-agent systems

    Researchers propose a method called Multi-Agent Goal Recognition with Branch-and-Bound (MAGR-BB) to infer the goals of multiple agents in real applications like drone surveillance and collaborative robotics, where only…

  22. Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound

    Source note · Jun 24, 2026 · ai, reinforcement learning, multi-agent systems

    The paper presents Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound (MAGR-BB), a method to infer which agents in a multi-agent system are working…

  23. Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents

    Source note · Jun 24, 2026 · reinforcement learning, llm agents, policy optimization

    The researchers propose a method called Semantic Consistency Policy Optimization (SCPO) to address a problem in reinforcement learning of LLM agents. The issue is that these agents are trained for long-term, sparse…

  24. WinDOM: Self-Family Distillation for Small-Model GUI Grounding

    Source note · Jun 24, 2026 · reinforcement learning

    Researchers have created a method called WinDOM for small GUI-grounding agents, which are useful for on-device deployment and accessibility tools. The method uses self-Family Distillation (SFD) to obtain bounding-box…

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.