57544b1ff9f97d4da9f64d25c8ea5a3d8d247ffc,rllib/examples/cartpole_lstm.py,,,#,5

Before Change

    tune.run(
        args.run,
        stop={"episode_reward_mean": args.stop},
        config=dict(
            configs[args.run], **{
                "env": StatelessCartPole,
                "model": {
                    "use_lstm": True,
                    "lstm_use_prev_action_reward": args.use_prev_action_reward,
                },
                "use_pytorch": args.torch,
            }),
    )

After Change

        },
    }

    config = dict(
        configs[args.run], **{
            "env": StatelessCartPole,
            "model": {
                "use_lstm": True,
                "lstm_use_prev_action_reward": args.use_prev_action_reward,
            },
            "use_pytorch": args.torch,
        })

    stop = {
        "training_iteration": args.stop_iters,
        "timesteps_total": args.stop_timesteps,

Instances