 |
Decision Boundary |
Pick up 20 Agents that are very aggressive |
2021-02-06 06:57:38 |
1.12 |
|
 |
Normalization |
Have all 5 agents consume in a single world. |
2021-02-06 06:57:38 |
1.12 |
|
 |
Adam Optimizer |
Have a Reinforcement Learning Agent survive to the end of the film |
2021-02-06 06:57:39 |
1.12 |
|
 |
Turing Test |
Have a Reinforcement Learning Agent to ascend to the next planet |
2021-02-06 06:57:40 |
1.12 |
|
 |
Loss Minimization |
Grab an Agent while they’re falling during the fall moment |
2021-02-06 06:57:40 |
1.12 |
|
 |
Computer Vision |
See all moments |
2021-02-06 06:57:40 |
1.12 |
|
 |
Unsupervised Learning |
Achieve a good ending without planting a MacGuffin |
2021-02-06 06:57:41 |
1.12 |
|
 |
Backpropagation |
Achieve a good ending 3 times in a row without planting any MacGuffins |
2021-02-06 06:57:41 |
1.12 |
|
 |
Gradient Descent |
Descend deep into the simulation |
2021-02-06 06:57:41 |
1.12 |
|
 |
Weights and Biases |
Cover the entire surface area of the planet with MacGuffin roots |
2021-02-06 06:57:41 |
1.12 |
|
 |
One-hot Encoding |
One interaction good ending |
2021-02-06 06:57:41 |
1.12 |
|
 |
NaN Trap |
All Agents fall off the planet |
2021-02-06 06:57:41 |
0.94 |
|
 |
Activation Function |
Achieve the Good Ending |
2021-02-06 06:57:42 |
1.12 |
|
 |
Learning Plateau |
MCG falls to bottom, no agents ascend |
2021-02-06 06:57:42 |
0.94 |
|
 |
A.G.I. |
All agents ascend |
2021-02-06 06:57:42 |
1.12 |
|
 |
Singularity |
5 RL agents ascend |
2021-02-06 06:57:42 |
1.12 |
|
