velocitatem/PHANTOM
1
0
Fork 0
mirror of https://github.com/velocitatem/PHANTOM.git synced 2026-05-31 08:33:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'agent-behavior-loader-developemen' into feat-strong-learning-implementation-with-data-contamination

Browse Source
This commit is contained in:
Daniel Alves Rösel
2026-01-31 10:08:59 +01:00
committed by GitHub
parent 26abff5864 72877439ca
commit 2f481bd94b
25 changed files with 1205 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
sim/rl/behavior_loader/models.py
View File

@@ -18,8 +18,6 @@ try:
except ImportError:
lib_make_state_repr = None
lib_transition_histogram = None
print("lib no includable")
class BehaviorModel:
@@ -226,7 +224,7 @@ if __name__ == "__main__":
agent_model = AgentBehaviorModel(agent_dir)
agent_mdp = agent_model.build_MDP()
print(agent_mdp)
print(f"AGENT... Built MDP: {agent_mdp['num_states']} states, "
f"{sum(len(t) for t in agent_mdp['transitions'].values())} transitions")
if not agent_mdp['states']:
@@ -235,8 +233,6 @@ if __name__ == "__main__":
human_evt = aggregate_event_transitions(human_mdp)
agent_evt = aggregate_event_transitions(agent_mdp)
print(agent_evt)
common = set(human_evt.keys()) & set(agent_evt.keys())

16
sim/rl/engine.py
View File

@@ -1,10 +1,10 @@
from os import kill
import numpy as np
import pandas as pd
from abc import ABC, abstractmethod
from typing import Dict, Any
from sim.rl.environment import BusinessLogicConstraints
"""
An angine by default should have its own demand estimation mechanism from the observed observations whihc are the computer feature.
From these features we then follow the researc hstructure of q -> p with a testable and must be updatable mechanism.
@@ -39,6 +39,7 @@ class BasePricingEngine(ABC):
def reset(self):
"""reset engine state for new episode"""
self.step_count = 0
@@ -68,15 +69,16 @@ class WildPricingEngine(BasePricingEngine):
def reset(self):
super().reset()
self.e_hat = np.full((self.c.product_catalogue_size,), -1.3, dtype=np.float32)
self.mu_logp = np.zeros(self.c.product_catalogue_size, dtype=np.float32)
self.mu_logq = np.zeros(self.c.product_catalogue_size, dtype=np.float32)
self.cov_pq = np.zeros(self.c.product_catalogue_size, dtype=np.float32)
self.var_p = np.ones(self.c.product_catalogue_size, dtype=np.float32)
self.e_hat = np.full((self.c.product_catelogue_size,), -1.3, dtype=np.float32)
self.mu_logp = np.zeros(self.c.product_catelogue_size, dtype=np.float32)
self.mu_logq = np.zeros(self.c.product_catelogue_size, dtype=np.float32)
self.cov_pq = np.zeros(self.c.product_catelogue_size, dtype=np.float32)
self.var_p = np.ones(self.c.product_catelogue_size, dtype=np.float32)
def compute_prices(self, current_prices: np.ndarray, observation: Dict[str, Any]) -> np.ndarray:
self.step_count += 1
demand = _extract_demand(observation, self.c.product_catalogue_size)
# extract demand signal (from env observation) as proxy for sales
demand = observation.get('demand', np.zeros(self.c.product_catelogue_size, dtype=np.float32))
return self._update_from_demand(current_prices, demand)
def _update_from_demand(self, prices: np.ndarray, sold: np.ndarray) -> np.ndarray: