Agent Curricula for Bootstrapped Complex Reinforcement Learning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Reinforcement learning systems face challenges in efficiently training complex neural networks to perform tasks due to high computational requirements and prolonged training times, especially when these networks require more training steps or are less robust to hyperparameter settings.

Innovation Solution

A curriculum-based approach is employed, where a set of candidate agent policy neural networks with varying complexity levels are trained jointly, with initial weights favoring simpler networks, gradually transitioning to more complex networks, leveraging simpler networks' solutions to accelerate the learning process of more complex networks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a complex neural network is trained to perform reinforcement learning tasks, then the agent can achieve higher performance capabilities, but the training time and computational resources required increase significantly

Engineering Contradiction:
Improveagent performance capabilityVSAvoidtraining time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by training simpler neural networks before the complex final network. The simpler networks are trained first to learn basic task components, and their learned policies are then used as initialization or guidance for training the more complex final network, thereby reducing the overall training time required to achieve high performance

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The training process is segmented into multiple stages with different network complexities. Instead of training one complex network from scratch, the patent divides the learning process into phases where simpler networks handle easier subtasks first, and the complex network gradually takes over, breaking down the complex training problem into manageable segments

Inventive Principle:
Principle #1Segmentation

2Adaptability or versatility

If a complex neural network with more parameters or larger action space is used, then the agent can perform more sophisticated tasks, but the training becomes more difficult and requires more training steps

Engineering Contradiction:
Improvetask complexity handlingVSAvoidnetwork complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

Simpler networks with fewer parameters are trained first to establish basic policy structures. These pre-trained simpler networks provide a head start for the complex network, reducing the difficulty of training sophisticated policies in the complex network without sacrificing task complexity handling capability

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent changes parameters progressively by adjusting network complexity, learning rates, and other hyperparameters across different training stages. The complex network is trained with parameter settings that leverage knowledge from simpler networks, making the training process more manageable despite the increased network complexity

Inventive Principle:
Principle #35Parameter changes

3Manufacturing precision

If training is performed on a single complex network in isolation, then the network can be optimized for the final task, but the training becomes prohibitively expensive and time-consuming

Engineering Contradiction:
Improvepolicy optimization qualityVSAvoidcomputational resources
Core Design Contradiction:
Manufacturing precisionVSUse of energy by moving object

Solution Approach 1:

The training workload is segmented across multiple simpler networks that are trained in parallel or sequence before the final complex network. This segmentation distributes the computational burden, reducing the energy required to train any single network while maintaining overall policy optimization quality through the progressive knowledge transfer

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent uses copying by initializing the complex network with parameters or policies learned from simpler networks. Instead of training the complex network from random initialization (which is computationally expensive), the system copies learned representations from simpler networks, significantly reducing the computational resources needed while preserving optimization quality

Inventive Principle:
Principle #26Copying

Data Source

PatentEP3776363B1Reinforcement learning using agent curricula
Publication Date: 2025.08.13 GDM HOLDING LLC
  • EP3776363B1 patent drawingFigure 1
  • EP3776363B1 patent drawingFigure 2A
  • EP3776363B1 patent drawingFigure 2B

AI summary

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning using agent curricula.