View RSS Feed

Recent Blogs Posts

  1. Neural networks made easy (Part 40): Using Go-Explore on large amounts of data

    by , 06-29-2024 at 07:22 AM
    In the previous article "Neural networks made easy (Part 39): Go-Explore, a different approach to exploration", we familiarized ourselves with the Go-Explore algorithm and its ability to explore the environment.

    In this article, we will take a closer look at possible optimization methods for the Go-Explore algorithm to improve its efficiency over longer training periods.
    more...
    Categories
    Uncategorized
  2. Neural networks made easy (Part 64): ConserWeightive Behavioral Cloning (CWBC) method

    by , 06-25-2024 at 06:27 AM
    The Decision Transformer and all its modifications, which we discussed in recent articles, belong to the methods of Behavior Cloning (BC). We train models to repeat actions from "expert" trajectories depending on the state of the environment and the target outcomes. Thus, we teach the model to imitate the behavior of an expert in the current state of the environment in order to achieve the target.
    more...
    Categories
    Uncategorized
  3. Neural networks made easy (Part 63): Unsupervised Pretraining for Decision Transformer (PDT)

    by , 06-21-2024 at 06:27 AM
    PDT jointly learns an embedding space of future trajectory as well as a future prior conditioned only on past information.. By conditioning action prediction on the target future embedding, PDT is endowed with the ability to "reason over the future". This ability is naturally task-independent and can be generalized to different task specifications.

    To achieve efficient online fine-tuning in downstream tasks, you can easily adapt the framework to new conditions by associating each
    ...
    Categories
    Uncategorized
  4. Neural networks made easy (Part 62): Using Decision Transformer in hierarchical models

    by , 06-19-2024 at 06:28 AM
    Previously, we considered hierarchical models for solving problems with, so to speak, the classical approach of the Markov process. However, the advantages of using hierarchical approaches also apply to sequence analysis problems. One such algorithm is the Control Transformer presented in the article "Control Transformer: Robot Navigation in Unknown Environments through PRM-Guided Return-Conditioned Sequence Modeling". The method authors position it as a new architecture designed to solve
    ...
    Categories
    Uncategorized
  5. Discrete Hartley transform

    by , 06-18-2024 at 02:15 PM
    In 1942, Ralph Hartley proposed an analogue of the Fourier transform in his article "A More Symmetrical Fourier Analysis Applied to Transmission Problems".
    Just like Fourier transform (FT), Hartley transform (HT) turns the original signal into a sum of trigonometric functions. But there is one significant difference between them. FT converts real values to complex numbers, while HT provides only real results. Because of this difference, the Hartley transform did not become popular - scientists
    ...
    Categories
    Uncategorized
Page 1 of 147 1 2 3 11 51 101 ... LastLast