diff --git a/examples/training_navigation.py b/examples/training_navigation.py index 7b35cb212f691287e0fff411d0a019fc8acd4059..b7e46c3985121aef27fb15f6843ba78f33dfe31a 100644 --- a/examples/training_navigation.py +++ b/examples/training_navigation.py @@ -62,7 +62,8 @@ for trials in range(1, n_trials + 1): env_done = 0 # Run episode - for step in range(100): + for step in range(50): + #env_renderer.renderEnv(show=True) # Action for a in range(env.number_of_agents): @@ -71,9 +72,6 @@ for trials in range(1, n_trials + 1): # Environment step next_obs, all_rewards, done, _ = env.step(action_dict) - - - # Update replay buffer and train agent for a in range(env.number_of_agents): agent.step(obs[a], action_dict[a], all_rewards[a], next_obs[a], done[a])