Tags¶
- Metadata: #topic
- Part of: Psychology [[Reinforcement learning]] Artificial intelligence safety Mathematical theory of artificial intelligence
- Related:
- Includes:
- Additional:
Significance¶
Intuitive summaries¶
Definitions¶
- Research program aimed at explaining the systematic relationships between the reinforcement schedules and learned values of reinforcement-learning agents
Technical summaries¶
Main resources¶
Landscapes¶
Contents¶
- Understanding and controlling a maze-solving policy network — LessWrong
- Steering GPT-2-XL by adding an activation vector — LessWrong
Deep dives¶
Brain storming¶
Additional resources¶
Related¶
Related resources¶
AI¶
Additional metadata¶
-
processed #processing #toprocess #important #short #long #casual #focus¶
- Unfinished: #metadata #tags