In Reinforcement Learning, what is the term for the tension between trying new actions to find better rewards and choosing known actions that yield high rewards?
Show answer
Exploration-exploitation tradeoff
Exploration involves searching the environment for more information, while exploitation uses current knowledge to maximize reward. Balancing these is a core challenge in RL, often managed by strategies like epsilon-greedy.
Also asked as:
- What term describes the Reinforcement Learning challenge of balancing the search for new information against using current knowledge to maximize rewards?