robopal.wrappers.petting_zoo_wrapper module

class robopal.wrappers.petting_zoo_wrapper.PettingStyleWrapper(env: MujocoEnv)

基类：ParallelEnv

The metadata holds environment constants.

The "name" metadata allows the environment to be pretty printed.

action_space(agent)

Takes in agent and returns the action space for that agent.

MUST return the same value for the same agent name

Default implementation is to return the action_spaces dict

metadata: dict[str, Any] = {'render_modes': ['human', 'rgb_array', 'depth', 'unity']}

observation_space(agent)

Takes in agent and returns the observation space for that agent.

MUST return the same value for the same agent name

Default implementation is to return the observation_spaces dict

render(mode=None)

Renders the environment.

reset(seed=None, options=None)

Reset set the environment to a starting point.

step(actions: Dict[str, ndarray])

Takes in an action for the current agent (specified by agent_selection).