AI engineering glossary · Reinforcement learning
What is goal-conditioned reinforcement learning?
Goal-conditioned reinforcement learning: A setting where the decision rule takes a desired goal as an additional input and is trained to reach whichever goal it is given. One learner can then serve many tasks, and relabelling goals gives more training signal.
Goal-conditioned reinforcement learning: an example
A robot arm policy takes the target block position as input and learns to place blocks anywhere.
Related terms
- Hindsight experience replay
- Sparse reward
- Policy (reinforcement learning)
- Universal value function
More Reinforcement learning terms
- Greedy policy
- Hierarchical reinforcement learning
- Hindsight experience replay
- Horizon
- Imitation learning
- Importance sampling ratio
- Intrinsic motivation
- Inverse reinforcement learning
Where you learn it
Goal-conditioned reinforcement learning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.