השוואת שיטות
סקרו את השיטות שבחרתם זו לצד זו; שורות שבהן יש הבדל מודגשות.
| תכנות דינמי מבוסס-סוכן× | למידת חיזוק× | |
|---|---|---|
| תחום≠ | סימולציה | למידה עמוקה |
| משפחה≠ | Process / pipeline | Machine learning |
| שנת המקור≠ | 1957 (DP); 1990s onward (ABM integration) | 1950s–1998 |
| הוגה השיטה≠ | Bellman, R. (DP foundation); Tesfatsion, L. et al. (ABM-DP integration) | Sutton, R. S. & Barto, A. G. (formalised); Bellman, R. (foundations) |
| סוג≠ | Hybrid simulation-optimization | Sequential decision-making framework |
| מקור מכונן≠ | Bellman, R. (1957). Dynamic Programming. Princeton University Press, Princeton, NJ. ISBN: 9780691079516 | Sutton, R. S. & Barto, A. G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. ISBN: 978-0-262-03924-6 |
| כינויים | ABDP, Agent-based DP, Multi-agent dynamic programming, ABM-DP | RL, reward-based learning, trial-and-error learning, policy optimization |
| קשורות≠ | 5 | 2 |
| תקציר≠ | Agent-based dynamic programming (ABDP) embeds Bellman's dynamic programming framework within individual agents of an agent-based model, enabling each agent to solve sequential, multi-stage decision problems using backward induction or value-function iteration. The result is a population of optimizing agents whose interactions generate emergent system-level behavior. | Reinforcement Learning (RL) is a framework in which an agent learns to make sequential decisions by interacting with an environment, receiving scalar reward signals, and updating a policy to maximise cumulative future reward. Unlike supervised learning, no labeled examples are provided; the agent discovers optimal behavior entirely through experience and delayed feedback. |
| ScholarGateמערך נתונים ↗ |
|
|