a90cd0fcbb81c2be472b16c61bebc75125d16133,rllib/examples/unity3d_env_local.py,,,#,29

Before Change

    policies, policy_mapping_fn = \
        Unity3DEnv.get_policy_configs_for_game(args.env)

    config = {
        "env": "unity3d",
        "env_config": {
            "episode_horizon": args.horizon,
        },
        // IMPORTANT: Just use one Worker (we only have one Unity running)!
        "num_workers": 0,
        // Other settings.
        "sample_batch_size": 64,
        "train_batch_size": 256,
        "rollout_fragment_length": 20,
        // Multi-agent setup for the particular env.
        "multiagent": {
            "policies": policies,
            "policy_mapping_fn": policy_mapping_fn,
        },
        "framework": "tf",
    }

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

After Change

    help="The Unity3d binary (compiled) game, e.g. "
    ""/home/ubuntu/soccer_strikers_vs_goalie_linux.x86_64". Use `None` for "
    "a currently running Unity3D editor.")
parser.add_argument(
    "--from-checkpoint",
    type=str,
    default=None,
    help="Full path to a checkpoint file for restoring a previously saved "
    "Trainer state.")
parser.add_argument("--num-workers", type=int, default=0)
parser.add_argument("--as-test", action="store_true")
parser.add_argument("--stop-iters", type=int, default=9999)
parser.add_argument("--stop-reward", type=float, default=9999.0)

Instances