A task is associating a purpose with an environment. It decides how to evaluate the
observations, potentially returning reinforcement rewards or fitness values.
Furthermore it is a filter for what should be visible to the agent.
Also, it can potentially act as a filter on how actions are transmitted to the environment.
- The function scales the parameters from -1 and 1 to the given interval (min, max) for each actor.
- A filtered mapping to getSample of the underlying environment.
- Compute and return the current reward (i.e. corresponding to the last action performed)
- The function scales the parameters to be between -1 and 1. e.g. [(-pi, pi), (0, 1), (-0.001, 0.001)]
- A filtered mapping towards performAction of the underlying environment.
- Expects scaling lists of 2-tuples - e.g. [(-3.14, 3.14), (0, 1), (-0.001, 0.001)] -
one tuple per parameter, giving min and max for that parameter. The functions
normalize and denormalize scale the parameters between -1 and 1 and vice versa.
To disable this feature, use ‘None’.