What should return to go be during inferencing? about decision-transformer HOT 2 CLOSED

From my understanding, after setting an initial target reward for the entire episode, for each reward we get after performing a step, we do

new_target_reward = target_reward - received_reward_from_env

Is this correct?

from decision-transformer.

1. In general there isn't a single way to pick RTG and it depends on the environment. You would probably sweep this value for experiments.
2. After every step you subtract the received reward, correct.

Multi-Game Decision Transformers (https://arxiv.org/abs/2205.15241) looks into learning the RTG like a value function, removing the need to specify it manually.

from decision-transformer.