{
  "patent_number": "US 20230037632",
  "country": "US",
  "title": "How AI Learns Better by Understanding Connections",
  "original_title": "Reinforcement learning method and apparatus",
  "summary": "This patent describes a method for artificial intelligence to learn more effectively by first creating a 'structure graph' that maps relationships in its world, then using a 'graph neural network' to make smarter decisions based on that map.",
  "what_it_does": "This patent describes a method for an 'intelligent agent' (like an AI program) to learn how to make decisions in an 'environment' (like a game or a robot's world). It starts by creating a 'structure graph' (Claim 1), which is like a map showing how different parts of the environment or the agent itself are connected. This map is learned from past interactions (Claim 2). The AI then uses this structure graph, along with what's currently happening in its environment, as input to its 'policy function' (Claim 1). This policy function, which is a 'graph neural network' (Claim 1), decides what action the AI should take. After taking an action, the AI gets feedback (a 'next state' and 'reward data'), which it uses to train itself and get better at making decisions (Claim 1). For example, in a robot control scenario (Claim 6), the robot might learn the physical connections between its parts or objects in its path, using this map to plan smoother movements.",
  "what_it_does_not_cover": [
    "Does not cover reinforcement learning methods where the policy function is not a graph neural network.",
    "Does not cover methods that do not explicitly obtain and use a 'structure graph' as an input to the policy function.",
    "Does not cover reinforcement learning where the structure graph is not learned from historical interaction data.",
    "Does not cover methods that do not involve training the agent through reinforcement learning based on reward data.",
    "Does not cover scenarios where the historical interaction data is not filtered to eliminate the impact of the agent's own actions (Claims 3, 4)."
  ],
  "filed": "2022-10-17",
  "granted": null,
  "expires": "2042-10-17",
  "status": "active",
  "holder": "Huawei Technologies Co",
  "holder_url": "https://patentbrief.org/company/huawei-technologies-co",
  "inventors": [
    {
      "name": "Wenjing CUN",
      "url": "https://patentbrief.org/inventor/wenjing-cun"
    },
    {
      "name": "Furui LIU",
      "url": "https://patentbrief.org/inventor/furui-liu"
    },
    {
      "name": "Zhitang Chen",
      "url": "https://patentbrief.org/inventor/zhitang-chen"
    }
  ],
  "times_cited": 11,
  "tags": [
    "ai_ml",
    "software",
    "robotics",
    "telecommunications",
    "gaming"
  ],
  "abstract": "A reinforcement learning method and recognition apparatus includes: obtaining a structure graph, where the structure graph includes structure information that is of an environment or the intelligent agent and that is obtained through learning; inputing a current state of the environment and the structure graph to a policy function of the intelligent agent, where the policy function is used to generate an action in response to the current state and the structure graph, and the policy function of the intelligent agent is a graph neural network; outputing the action to the environment by using the intelligent agent; obtaining, from the environment by using the intelligent agent, a next state and reward data in response to the action; training the intelligent agent through reinforcement learning based on the reward data.",
  "url": "https://patentbrief.org/patent/us/20230037632/reinforcement-learning-method-and-apparatus",
  "markdown_url": "https://patentbrief.org/patent/us/20230037632/reinforcement-learning-method-and-apparatus/md",
  "google_patents_url": "https://patents.google.com/patent/US20230037632",
  "relatedPatents": [
    {
      "patentNumber": "12245052",
      "countryCode": "US",
      "title": "Using AI to Manage Wireless Network Resources Smarter",
      "url": "https://patentbrief.org/patent/us/12245052/reinforcement-learning-rl-and-graph-neural-network-gnn-based-resource-management"
    },
    {
      "patentNumber": "9754221",
      "countryCode": "US",
      "title": "A Computer Chip for Training Many AI Agents at Once",
      "url": "https://patentbrief.org/patent/us/9754221/processor-for-implementing-reinforcement-learning-operations"
    },
    {
      "patentNumber": "11120365",
      "countryCode": "US",
      "title": "How AI Models Learn Complex Tasks by Breaking Them Down",
      "url": "https://patentbrief.org/patent/us/11120365/for-hierarchical-decomposition-deep-reinforcement-learning-for-an-artificial-int"
    },
    {
      "patentNumber": "10282665",
      "countryCode": "US",
      "title": "How AI Agents Learn to Pick the Best Future Actions",
      "url": "https://patentbrief.org/patent/us/10282665/action-selection-with-a-reward-estimator-applied-to-machine-learning"
    },
    {
      "patentNumber": "11836577",
      "countryCode": "US",
      "title": "Training Robot AI Models Faster Using Smart Simulations",
      "url": "https://patentbrief.org/patent/us/11836577/reinforcement-learning-model-training-through-simulation"
    }
  ]
}