17 lines
654 B
Python
17 lines
654 B
Python
from agents.offline_agent import QLearningAgent
|
|
from negotiation_agent.environment import NegotiationEnv
|
|
|
|
class EvaluateAgentUseCase:
|
|
def execute(self, agent: QLearningAgent, env: NegotiationEnv, num_episodes: int):
|
|
total_rewards = 0
|
|
for _ in range(num_episodes):
|
|
obs, _ = env.reset()
|
|
episode_reward = 0
|
|
terminated = False
|
|
while not terminated:
|
|
action = agent.get_action(obs)
|
|
obs, reward, terminated, _, _ = env.step(action)
|
|
episode_reward += reward
|
|
total_rewards += episode_reward
|
|
return total_rewards / num_episodes
|