tensortrade.env.generic.components.reward_scheme module¶

class tensortrade.env.generic.components.reward_scheme.RewardScheme(*args, **kwargs)[source]¶

Bases: tensortrade.core.component.Component, tensortrade.core.base.TimeIndexed

A component to compute the reward at each step of an episode.

registered_name = 'rewards'¶

reset() → None [source]¶: Resets the reward scheme.

abstract reward(env: TradingEnv) → float [source]¶

Computes the reward for the current step of an episode.

Parameters: env (TradingEnv) – The trading environment
Returns: float – The computed reward.