`hyphi_gym.common.point`#

Module Contents#

Classes#

Base class for Continous Control in Board Games

Attributes#

`SIZE`
`HEIGHT`
`AGENT_SIZE`

hyphi_gym.common.point.SIZE = 1.0#

hyphi_gym.common.point.HEIGHT = 1.0#

hyphi_gym.common.point.AGENT_SIZE = 0.3#

class hyphi_gym.common.point.Point(grid=False, render_mode=None, frame_skip=1)#

Bases: hyphi_gym.common.simulation.Simulation

Base class for Continous Control in Board Games Use for 3D simulation of continuous board envs and rendering of grids

property default_cam_config#

property agent: tuple[hyphi_gym.common.board.np.ndarray, hyphi_gym.common.board.np.ndarray]#: Get noisy initial agent position and velocity

step_scale = 10#

base_xml#

metadata#

state_vector() → hyphi_gym.common.board.np.ndarray#: Return the position and velocity joint states of the model

execute(action: hyphi_gym.common.board.np.ndarray) → tuple[dict, dict]#: Executes the action, returns the new state, info, and distance between the agent and target

reset(**kwargs)#: Reset the environment simulation and randomize if needed

setup_world(layout=None)#: Helper function to generate a simulation from a board-based layout

load_world()#: Helper function to load a generated world from self.model_path falling back to self.base_xml

_toggle_target(active: hyphi_gym.common.board.Optional[bool] = None)#: Toggles activity of the target site, can be forced using active

update_world(action: int, position: hyphi_gym.common.board.Union[hyphi_gym.common.board.np.ndarray, tuple], cell: str)#

reset_world()#: Reset simulation and reposition agent and target to respective i_pos

_update(key: str, oldpos, newpos)#