fix reward in chess.json

[w9PcJLyb]

Because, at this moment, I can't initialize chess environment with steps if the game's result was a draw.

>>> kaggle_environments.make("chess", steps=game["steps"])

raise InvalidArgument(
kaggle_environments.errors.InvalidArgument: Default state generation failed for #0: 0.5 is not one of [-1, 0, 1]

Failed validating 'enum' in schema['properties']['reward']:
    {'description': '-1 = Lost, 0 = Draw/Ongoing, 1 = Won',
     'type': ['number', 'null'],
     'default': 0,
     'enum': [-1, 0, 1]}

On instance['reward']:
    0.5

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[bovard]

LGTM, thanks!