Results for "shared reward"
Exploration-Exploitation Tradeoff
Intermediate
Balancing learning new behaviors vs exploiting known rewards.
Alignment Problem
Advanced
Ensuring AI systems pursue intended human goals.
Inner Alignment
Advanced
Ensuring learned behavior matches intended objective.
Imitation Learning
Advanced
Learning policies from expert demonstrations.
Deceptive Alignment
Advanced
Model behaves well during training but not deployment.
Power-Seeking Behavior
Advanced
Tendency to gain control/resources.
Value Learning
Intermediate
Inferring and aligning with human preferences.
On-Policy Learning
Intermediate
Learning only from current policy’s data.