Glossary · Robotics and Physical AI
Reinforcement Learning
Learning by trial and error, where an agent tries actions, receives rewards or penalties and adjusts its behavior.
How it connects
Includes
Is a type of
Types of this
- Actor-Critic
- Deep Reinforcement Learning (Deep RL)
- Hierarchical Reinforcement Learning (HRL)
- Model-Based Reinforcement Learning (MBRL)
- Model-Free Reinforcement Learning
- Monte Carlo Methods (MC)
- Multi-Agent Reinforcement Learning (MARL)
- Off-Policy Learning
- Offline Reinforcement Learning (Offline RL)
- On-Policy Learning
- Online Reinforcement Learning
- Policy Gradient
- Safe Reinforcement Learning (Safe RL)
- Temporal Difference Learning (TD)
Also in another glossary
- Reinforcement Learning (RL), Manufacturing glossary
Where it appears
In the Learning Center:
Full entry
Every term has a full entry for members: the plain-words definition, the practitioner note, the standards and the organizations behind it. Visitors without a membership can open five full entries in any 30 days.
ACW Robotics and Physical AI Glossary, edition 2026.11.1. The headword and one line are open to everyone.