db09dc1fb503ab8f7de69fa23e8d38742bda8e90,ch07/02_dqn_n_steps.py,,,#,12

Before Change

    env = ptan.common.wrappers.wrap_dqn(env)

    writer = SummaryWriter(comment="-" + params["run_name"] + "-%d-step" % args.n)
    net = dqn_model.DQN(env.observation_space.shape, env.action_space.n)
    if args.cuda:
        net.cuda()

    tgt_net = ptan.agent.TargetNet(net)
    selector = ptan.actions.EpsilonGreedyActionSelector(epsilon=params["epsilon_start"])
    epsilon_tracker = common.EpsilonTracker(selector, params)
    agent = ptan.agent.DQNAgent(net, selector, cuda=args.cuda)

After Change

    parser.add_argument("--cuda", default=False, action="store_true", help="Enable cuda")
    parser.add_argument("-n", default=REWARD_STEPS_DEFAULT, type=int, help="Count of steps to unroll Bellman")
    args = parser.parse_args()
    device = torch.device("cuda" if args.cuda else "cpu")

    env = gym.make(params["env_name"])
    env = ptan.common.wrappers.wrap_dqn(env)

    writer = SummaryWriter(comment="-" + params["run_name"] + "-%d-step" % args.n)
    net = dqn_model.DQN(env.observation_space.shape, env.action_space.n).to(device)

    tgt_net = ptan.agent.TargetNet(net)
    selector = ptan.actions.EpsilonGreedyActionSelector(epsilon=params["epsilon_start"])
    epsilon_tracker = common.EpsilonTracker(selector, params)

Instances