mirror of
https://github.com/blackboxprogramming/lucidia.git
synced 2026-03-19 15:21:09 -05:00
Alexa Amundson
855585cb0e
Synced from BlackRoad-OS-Inc/blackroad-operator/orgs/personal/lucidia BlackRoad OS — Pave Tomorrow. RoadChain-SHA2048: fe729062952871e7 RoadChain-Identity: alexa@sovereign RoadChain-Full: fe729062952871e77147cf6d938b799096e87d9024d7005a14c9e209e12e8ad0c825b624c7bc649fc7eeb4c284fdcab8231af77980065cc04d9f36fca479ffc2346ed3c1b73de6f240d8f9485f47c995ad5b81142f7179b84932c67914dff1c08db039349ba28fca36cb57688093bf0199268dd1c2f3448c9383000bc77cc9663066ff57b834370afc8838b18466ea9029908018b961555cccaabf2ce21649cf3cabc7f64bdcc4abdf2da259b210c342835a2cecf92bdd3b4e109b4d6e622f6934e13b2b123607bd61ce3d0f20454c9ab594f9284cffe18716619c52db57ce5f4ee2856cb96e1fa3748fe1fe65435bec297c5ab3ab58d570ec1064aea29931dd
60 lines
1.7 KiB
Python
60 lines
1.7 KiB
Python
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
from typing import Any, Callable, List
|
|
|
|
@dataclass
|
|
class LearningCycle:
|
|
"""
|
|
Represents a single learning cycle iteration.
|
|
|
|
Attributes
|
|
----------
|
|
iteration : int
|
|
The iteration number (starting from 1).
|
|
state : Any
|
|
The state after the update function is applied.
|
|
reward : float
|
|
The reward computed for this cycle.
|
|
"""
|
|
iteration: int
|
|
state: Any
|
|
reward: float
|
|
|
|
class LearningLoop:
|
|
"""
|
|
Executes an iterative learning loop with update and reward functions.
|
|
"""
|
|
def __init__(self, update_fn: Callable[[Any], Any], reward_fn: Callable[[Any], float], max_iter: int = 5) -> None:
|
|
self.update_fn = update_fn
|
|
self.reward_fn = reward_fn
|
|
self.max_iter = max_iter
|
|
|
|
def run(self, initial_state: Any) -> List[LearningCycle]:
|
|
"""
|
|
Run the learning loop over a number of iterations.
|
|
|
|
Parameters
|
|
----------
|
|
initial_state : Any
|
|
The starting state for the learning process.
|
|
|
|
Returns
|
|
-------
|
|
List[LearningCycle]
|
|
A list of learning cycles capturing state and reward at each step.
|
|
"""
|
|
cycles: List[LearningCycle] = []
|
|
state = initial_state
|
|
for i in range(1, self.max_iter + 1):
|
|
state = self.update_fn(state)
|
|
reward = self.reward_fn(state)
|
|
cycles.append(LearningCycle(i, state, reward))
|
|
return cycles
|
|
|
|
if __name__ == "__main__":
|
|
# Example usage: increment state and reward as negative distance from target 10
|
|
loop = LearningLoop(lambda x: x + 1, lambda x: -abs(10 - x), max_iter=3)
|
|
for cycle in loop.run(0):
|
|
print(cycle)
|