flexibot 0.1.2

A reinforcement learning library for robotics.

Flexibot

This is an efficient Python library made for the intended use of reinforcement learning in robotics.

!!WARNING THIS LIBRARY IS NOT FOR THE USE OF LLMS or Agents (e.g. ChatGPT, Gemini)!!

Installation

pip install flexibot

Example of how Flexibot is used

import flexibot as fl

isizess = [(1, 10), (1, 5), (1, 4), (1, 8)]
wsizess = [(10, 5), (5, 4), (4, 8), (8, 2)]  # Inner numbers match input columns!
bsizess = [(1, 5),  (1, 4), (1, 8), (1, 2)]

model = fl.network(isizes=isizess, wsizes=wsizess, bsizes=bsizess)

model.ReLU(activate=True)

while True:
    g = model.MatrixMultiplication(2)

    l, err = model.MSE(10)

    fg = model.Smoothen(1.2)
    print(fg)
    if l < 0.001:
        print(f"Success final answer {fg}")
        break
    else:
        model.Optim(0.01)

License

MIT License