Version 1.0

[jgillick]

This is a major version that cleans up some syntax and removes deprecated items. See the UPGRADE.md file for the full instructions on upgrading your environments.

List of changes in this branch, and pending work planned for v1.0:

• BREAKING: Requires Genesis World 1.3.0+
• Add velocity action manager and wheeled robot example
• Remove deprecated params
• Refactor how MDP functions and param syntax.
• Remove *_attr params
• Add unit test coverage
• Added imu_projected_gravity observation
• A 4-wheel robot as the wheeled_robot example.
• Added angular velocity to the velocity command debug indicators
  
• Fix envs_idx to be a tensor type on all managers and mdp reset functions
• Fix action delay setup/reset
• Fix class name type: SkrlEnvWapper -> SkrlEnvWrapper
• Velocity tracking reward sensitivity can be automatically derived from the command range
• A robot with ultrasonic range sensors
• Position manager
• Rewards for target position
• Add support for list of entities to contact manager
• Action managers can drive several joints from one action
• NOTE: Fixed a bug to clear previous step values (observations, terminations, actions, etc) on reset. Your environment might need to enable obs_normalization=True if they stop reaching convergence after this change.
• Fix: Observation noise is applied before scaling

MDP Functions (rewards, terminations, observations, entity resets)

This is the biggest change in this version. We're deprecating the params dictionaries in favor of data classes. For example:

Before

RewardManager(
    self,
    cfg={
        "base_height_target": {
            "weight": -50.0,
            "fn": rewards.base_height,
            "params": {
                "target_height": 0.3,
                "entity_attr": "robot",
            },
        },
    }
);

After

RewardManager(
    self,
    cfg={
        "base_height_target": {
            "weight": -50.0,
            "fn": rewards.base_height(
                target_height=0.3, 
                entity_attr="robot"
            ),
        },
    }
);

Note that params are passed directly into base_height. This allows for easier type checking and IDE autocomplete. Before, you'd need to open the mdp function documentation to get the list of params to type into the params dict.

This also changes how you write custom class-based MDP functions. Now they look like this:

@dataclass(kw_only=True, eq=False)
class lin_vel_z_l2(MdpFn):
    entity_manager: EntityManager = None

    def __call__(self, env: GenesisEnv) -> torch.Tensor:
        linear_vel = self.entity_manager.get_linear_velocity()
        return torch.square(linear_vel[:, 2])