| … | … | @@ -149,6 +149,7 @@ if __name__ == "__main__": |
| 149 | 149 | # Training/learning loop |
| 150 | 150 | lt_iterations = 2 # Number of learning-training iterations |
| 151 | 151 | lt_period = 200 # Duration of a learning-training iteration |
| 152 | max_cycle_count = cag.cycle_count + lt_iterations * lt_period |
| 152 | 153 | for i in range(lt_iterations): |
| 153 | 154 | wrapped_env.restart() |
| 154 | 155 | cag.reset_action_counter() |
| … | … | @@ -166,7 +167,7 @@ if __name__ == "__main__": |
| 166 | 167 | time.sleep(0.1) |
| 167 | 168 | agent_log.info( |
| 168 | 169 | "Control cycle ({}/{})".format( |
| 169 | | cag.cycle_count, lt_iterations * lt_period |
| 170 | cag.cycle_count, max_cycle_count |
| 170 | 171 | ) |
| 171 | 172 | ) |
| 172 | 173 | nar = cag.accumulated_reward - par |