search

blavad / marl

Multi-agent reinforcement learning framework
https://www.david-albert.fr/marl
29 stars 8 forks source link

'MARL' object has no attribute 'experience' #8

Open santiagoparaella opened 3 years ago

santiagoparaella commented 3 years ago

After the installation of both Soccer and marl i tried to run the second example with the MinMaxQAgent but I got the error: AttributeError: 'MARL' object has no attribute 'experience'

Following the Traceback:

> Start learning process.

| Date : 16/06/2021 12:28:09 Traceback (most recent call last): File "prova.py", line 30, in mas.learn(env, nb_timesteps=100000) File "/home/tiago/Scrivania/Libri magistrale/Tesi/Cidici Git/marl/marl/agent/agent.py", line 265, in learn self.update_model(timestep) File "/home/tiago/Scrivania/Libri magistrale/Tesi/Cidici Git/marl/marl/marl.py", line 85, in update_model ag.update_model(t) File "/home/tiago/Scrivania/Libri magistrale/Tesi/Cidici Git/marl/marl/agent/q_agent.py", line 53, in update_model batch = self.mas.experience.get_transition(len(self.mas.experience) - np.array(ind)-1) AttributeError: 'MARL' object has no attribute 'experience'

prova.py contains the code of the second example that is the following (the same of the README):

import marl from marl import MARL from marl.agent import MinimaxQAgent from marl.exploration import EpsGreedy

from soccer import DiscreteSoccerEnv # Environment available here "https://github.com/blavad/soccer" env = DiscreteSoccerEnv(nb_pl_team1=1, nb_pl_team2=1)

obs_s = env.observation_space act_s = env.action_space

# Custom exploration process expl1 = EpsGreedy(eps_deb=1.,eps_fin=.3) expl2 = EpsGreedy(eps_deb=1.,eps_fin=.3)

# Create two minimax-Q agents q_agent1 = MinimaxQAgent(obs_s, act_s, act_s, exploration=expl1, gamma=0.9, lr=0.001, name="SoccerJ1") q_agent2 = MinimaxQAgent(obs_s, act_s, act_s, exploration=expl2, gamma=0.9, lr=0.001, name="SoccerJ2")

# Create the trainable multi-agent system mas = MARL(agents_list=[q_agent1, q_agent2])

# Assign MAS to each agent q_agent1.set_mas(mas) q_agent2.set_mas(mas)

# Train the agent for 100 000 timesteps mas.learn(env, nb_timesteps=100000)

# Test the agents for 10 episodes mas.test(env, nb_episodes=10, time_laps=0.5)

Thank you in advance