Tensorboard support added

reinforcement_learning/multi_agent_training.py

@@ -504,7 +504,7 @@ def eval_policy(env, tree_observation, policy, train_params, obs_params):
 
 if __name__ == "__main__":
     parser = ArgumentParser()
-    parser.add_argument("-n", "--n_episodes", help="number of episodes to run", default=12000, type=int)
+    parser.add_argument("-n", "--n_episodes", help="number of episodes to run", default=5000, type=int)
     parser.add_argument("-t", "--training_env_config", help="training config id (eg 0 for Test_0)", default=1,
                         type=int)
     parser.add_argument("-e", "--evaluation_env_config", help="evaluation config id (eg 0 for Test_0)", default=1,