# | Unlocked | Locked | Name | Beschreibung | Spieler | Global |
---|---|---|---|---|---|---|
1 |
![]() |
![]() | Learning Plateau | MCG falls to bottom, no agents ascend | 1 | 29.5% |
2 |
![]() |
![]() | NaN Trap | All Agents fall off the planet | 1 | 28.5% |
3 |
![]() |
![]() | Adam Optimizer | Have a Reinforcement Learning Agent survive to the end of the film | 0 | 25.3% |
4 |
![]() |
![]() | Loss Minimization | Grab an Agent while they’re falling during the fall moment | 0 | 23.5% |
5 |
![]() |
![]() | Activation Function | Achieve the Good Ending | 0 | 19.8% |
6 |
![]() |
![]() | Normalization | Have all 5 agents consume in a single world. | 0 | 18% |
7 |
![]() |
![]() | Unsupervised Learning | Achieve a good ending without planting a MacGuffin | 0 | 17.7% |
8 |
![]() |
![]() | Gradient Descent | Descend deep into the simulation | 0 | 17.6% |
9 |
![]() |
![]() | A.G.I. | All agents ascend | 0 | 17.6% |
10 |
![]() |
![]() | Turing Test | Have a Reinforcement Learning Agent to ascend to the next planet | 0 | 17.2% |
11 |
![]() |
![]() | Computer Vision | See all moments | 0 | 17.1% |
12 |
![]() |
![]() | Decision Boundary | Pick up 20 Agents that are very aggressive | 0 | 16.8% |
13 |
![]() |
![]() | Backpropagation | Achieve a good ending 3 times in a row without planting any MacGuffins | 0 | 16.6% |
14 |
![]() |
![]() | Weights and Biases | Cover the entire surface area of the planet with MacGuffin roots | 0 | 16.6% |
15 |
![]() |
![]() | One-hot Encoding | One interaction good ending | 0 | 16.6% |
16 |
![]() |
| Singularity | 5 RL agents ascend | 0 | 16.6% |