1. yellow (no explicit instructions) was never gaining any rewards from learning.
2. red (added one extra sentence) started to improve and explore the reward.
3. green (added a whole sentence) best performance.
prompting matters i guess.
1. yellow (no explicit instructions) was never gaining any rewards from learning.
2. red (added one extra sentence) started to improve and explore the reward.
3. green (added a whole sentence) best performance.
prompting matters i guess.