Celes Renata
57619860d5
Complete implementation of the DCOS package including: - 40+ Python source files across agents, communication, core, learning, memory, protocols, utils - pyproject.toml build configuration - 102 unit tests across all subsystems - Fixed flake.nix (Python 3.12, proper dependencies, pyproject build) - Fixed .woodpecker.yml (correct paths, removed silent-fail flags) - Added .gitignore - Cleared stale pytest cache
45 lines
1.3 KiB
Python
45 lines
1.3 KiB
Python
"""
|
|
Learning engine — reinforcement learning and model updates for agents.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
from typing import Any, Dict, List, Optional
|
|
from dataclasses import dataclass, field
|
|
|
|
|
|
@dataclass
|
|
class Experience:
|
|
state: Dict[str, Any]
|
|
action: str
|
|
reward: float
|
|
next_state: Optional[Dict[str, Any]] = None
|
|
|
|
|
|
class LearningEngine:
|
|
"""Reinforcement learning engine that improves agent behavior over time."""
|
|
|
|
def __init__(self) -> None:
|
|
self._experiences: List[Experience] = []
|
|
self._policy: Dict[str, float] = {}
|
|
|
|
def record_experience(self, exp: Experience) -> None:
|
|
self._experiences.append(exp)
|
|
self._update_policy(exp)
|
|
|
|
def _update_policy(self, exp: Experience) -> None:
|
|
current = self._policy.get(exp.action, 0.0)
|
|
self._policy[exp.action] = current + exp.reward * 0.1
|
|
|
|
def get_action_score(self, action: str) -> float:
|
|
return self._policy.get(action, 0.0)
|
|
|
|
def best_action(self, actions: List[str]) -> Optional[str]:
|
|
if not actions:
|
|
return None
|
|
scored = [(a, self._policy.get(a, 0.0)) for a in actions]
|
|
scored.sort(key=lambda x: x[1], reverse=True)
|
|
return scored[0][0]
|
|
|
|
def experience_count(self) -> int:
|
|
return len(self._experiences)
|