diff --git a/examples/training_example.py b/examples/training_example.py index dd9ded92510be8ec5fa6c222b7259157db920430..313920939aabb8bc63b2198ff77d27a24d699468 100644 --- a/examples/training_example.py +++ b/examples/training_example.py @@ -80,7 +80,6 @@ for trials in range(1, n_trials + 1): # Environment step which returns the observations for all agents, their corresponding # reward and whether their are done next_obs, all_rewards, done, _ = env.step(action_dict) - # Update replay buffer and train agent for a in range(env.get_num_agents()): agent.step((obs[a], action_dict[a], all_rewards[a], next_obs[a], done[a]))