1646ac6e24a0c760f7e2d232169dbf42dc4acfb8,ch13/wob_click_train.py,,,#,20

Before Change

                // calculate policy gradients only
                loss_policy_v.backward(retain_graph=True)
                grads = np.concatenate([p.grad.data.cpu().numpy().flatten()
                                        for p in net.parameters()
                                        if p.grad is not None])

                // apply entropy and value gradients
                loss_v = entropy_loss_v + loss_value_v

After Change

    parser.add_argument("--port-ofs", type=int, default=0, help="Offset for container"s ports, default=0")
    parser.add_argument("--env", default=ENV_NAME, help="Environment name to solve, default=" + ENV_NAME)
    parser.add_argument("--demo", help="Demo dir to load. Default=No demo")
    parser.add_argument("--host", default="localhost", help="Host with docker containers")
    args = parser.parse_args()

    env_name = args.env
    if not env_name.startswith("wob.mini."):

Instances