sb3 switch

tutorials/13_lines.py

@@ -1,5 +1,5 @@
-from stable_baselines.common.policies import CnnPolicy
-from stable_baselines import PPO2
+from stable_baselines3.common.policies import CnnPolicy
+from stable_baselines3 import PPO2
 from pettingzoo.butterfly import pistonball_v4
 import supersuit as ss
 
@@ -10,7 +10,7 @@
 env = ss.pettingzoo_env_to_vec_env_v0(env)
 env = ss.concat_vec_envs_v0(env, 8, num_cpus=4, base_class='stable_baselines')
 
-model = PPO2(CnnPolicy, env, verbose=3, gamma=0.99, n_steps=125, ent_coef=0.01, learning_rate=0.00025, vf_coef=0.5, max_grad_norm=0.5, lam=0.95, nminibatches=4, noptepochs=4, cliprange=0.2, cliprange_vf=1)
+model = PPO(CnnPolicy, env, verbose=3, gamma=0.99, n_steps=125, ent_coef=0.01, learning_rate=0.00025, vf_coef=0.5, max_grad_norm=0.5, lam=0.95, nminibatches=4, noptepochs=4, cliprange=0.2, cliprange_vf=1)
 model.learn(total_timesteps=2000000)
 model.save("policy")
 
@@ -21,7 +21,7 @@
 env = ss.resize_v0(env, x_size=84, y_size=84)
 env = ss.frame_stack_v1(env, 3)
 
-model = PPO2.load("policy")
+model = PPO.load("policy")
 
 env.reset()
 for agent in env.agent_iter():