scml.std.rl.reward

Classes

`DefaultRewardFunction`	The default reward function of SCML
`RewardFunction`	Represents a reward function.

class scml.std.rl.reward.DefaultRewardFunction[source]

The default reward function of SCML

Remarks:

The reward is the difference between the balance before the action and after it.

Called before executing the action from the RL agent to save any required information for calculating the reward in its return

Remarks:: The returned value will be passed as info to __call__() when it is time to calculate the reward.

__call__(awi: scml.oneshot.awi.OneShotAWI, action: dict[str, negmas.SAOResponse], info: float)[source]

Called to calculate the reward to be given to the agent at the end of a step.

Parameters:

awi – OneShotAWI to access the agent’s state
action – The action (decoded) as a mapping from partner ID to responses to their last offer.
info – Information generated from before_action(). You an use this to store baselines for calculating the reward

Returns:

The reward (a number) to be given to the agent at the end of the step.

class scml.std.rl.reward.RewardFunction[source]

Bases: Protocol

Represents a reward function.