57544b1ff9f97d4da9f64d25c8ea5a3d8d247ffc,rllib/examples/nested_action_spaces.py,,,#,12

Before Change

    trainer = ppo.PPOTrainer(config=config)
    for _ in range(100):
        results = trainer.train()
        print(results)
        if results["episode_reward_mean"] > args.stop:
            sys.exit(0)  // Learnt, exit gracefully.
    sys.exit(1)  // Done, but did not learn, exit with error.

After Change

        "timesteps_total": args.stop_timesteps,
    }

    results = tune.run(args.run, config=config, stop=stop)

    if args.as_test:
        check_learning_achieved(results, args.stop_reward)

Instances