data/envs/atari/create_atari_dataset.py [47:72]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    render_mode = "human"
    if cfg.save_video:
        render_mode = "rgb_array"
    elif cfg.no_render:
        render_mode = None

    env = make_env_func_batched(
        cfg, env_config=AttrDict(worker_index=0, vector_index=0, env_id=0), render_mode=render_mode
    )
    env_info = extract_env_info(env, cfg)

    if hasattr(env.unwrapped, "reset_on_init"):
        # reset call ruins the demo recording for VizDoom
        env.unwrapped.reset_on_init = False

    actor_critic = create_actor_critic(cfg, env.observation_space, env.action_space)
    actor_critic.eval()

    device = torch.device("cpu" if cfg.device == "cpu" else "cuda")
    actor_critic.model_to_device(device)

    policy_id = cfg.policy_index
    name_prefix = {"latest": "checkpoint", "best": "best"}[cfg.load_checkpoint_kind]
    checkpoints = Learner.get_checkpoints(Learner.checkpoint_dir(cfg, policy_id), f"{name_prefix}_*")
    checkpoint_dict = Learner.load_checkpoint(checkpoints, device)
    actor_critic.load_state_dict(checkpoint_dict["model"])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



data/envs/mujoco/create_mujoco_dataset.py [82:107]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    render_mode = "human"
    if cfg.save_video:
        render_mode = "rgb_array"
    elif cfg.no_render:
        render_mode = None

    env = make_env_func_batched(
        cfg, env_config=AttrDict(worker_index=0, vector_index=0, env_id=0), render_mode=render_mode
    )
    env_info = extract_env_info(env, cfg)

    if hasattr(env.unwrapped, "reset_on_init"):
        # reset call ruins the demo recording for VizDoom
        env.unwrapped.reset_on_init = False

    actor_critic = create_actor_critic(cfg, env.observation_space, env.action_space)
    actor_critic.eval()

    device = torch.device("cpu" if cfg.device == "cpu" else "cuda")
    actor_critic.model_to_device(device)

    policy_id = cfg.policy_index
    name_prefix = {"latest": "checkpoint", "best": "best"}[cfg.load_checkpoint_kind]
    checkpoints = Learner.get_checkpoints(Learner.checkpoint_dir(cfg, policy_id), f"{name_prefix}_*")
    checkpoint_dict = Learner.load_checkpoint(checkpoints, device)
    actor_critic.load_state_dict(checkpoint_dict["model"])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -