Võrdle meetodeid
Vaata valitud meetodeid kõrvuti; erinevad read on esile tõstetud.
| Valdkonnaspetsiifiline tugevdatud õppimine× | Süva tugevdamisõpe× | |
|---|---|---|
| Valdkond | Süvaõpe | Süvaõpe |
| Perekond | Machine learning | Machine learning |
| Tekkeaasta≠ | 2009–2020 | 2015 |
| Looja≠ | Multiple contributors (Taylor & Stone 2009 survey; Kim et al. 2020 among key formalizations) | Mnih, V. et al. (DQN) |
| Tüüp≠ | Transfer-based RL paradigm | Sequential decision-making (agent–environment interaction) |
| Algallikas≠ | Kim, K., Kim, H., Lim, H., & Choi, J. (2020). Domain Adaptive Reinforcement Learning with Model-Based Approach. arXiv preprint arXiv:2102.03170. link ↗ | Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗ |
| Rööpnimetused≠ | Domain-Adaptive RL, DARL, Cross-domain RL, Transfer RL with domain adaptation | Derin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL |
| Seotud≠ | 2 | 4 |
| Kokkuvõte≠ | Domain-Adaptive Reinforcement Learning (DARL) extends standard RL by enabling a policy trained in one environment or domain to transfer and generalise effectively to a different but related target domain. It addresses the domain-shift problem — where dynamics, observations, or reward structures differ between training and deployment — through alignment, adaptation, or domain-randomisation techniques, reducing the need to collect costly experience in the target domain. | Deep Reinforcement Learning combines neural networks with reinforcement learning so an agent learns by interacting with an environment, popularised by Mnih and colleagues' 2015 Nature work on human-level Atari control. Instead of learning from a fixed labelled dataset, the agent takes actions, observes rewards, and gradually shapes a policy that maximises long-run return. |
| ScholarGateAndmestik ↗ |
|
|