Curriculum learning
Curriculum learning is a training strategy that presents tasks or examples in an organized progression, typically from easier to more difficult cases.
Applied Reinforcement Learning
Curriculum learning trains a model by beginning with simpler tasks or environments and progressively increasing their difficulty.
- How it is used
- Uses progressively harder environments to support DQN training for simulated treatment optimization.
- How deep it goes
- Specifies an episode-based difficulty schedule and environment parameters, alongside a success-rate guideline for progression.
- Examples
- Uses a radiotherapy simulation that adjusts dose noise, tumor dynamics, and organ-dose thresholds over 1,000 episodes.
- What you can do after
- Operate/configure a simulated training curriculum with episode-based or success-rate-based progression.
Read how Applied Reinforcement Learning explains curriculum learning →
Sutskever's List
Curriculum learning is a training strategy that presents examples in an organized progression, typically from easier to more difficult cases.
- How it is used
- Orders speech-training examples to make early training more stable and efficient.
- How deep it goes
- Explains first-epoch length sorting and its rationale, but does not specify an ordering procedure for later epochs.
- Examples
- Uses SortaGrad’s shorter-first ordering of Deep Speech 2 utterances as the concrete example.
- What you can do after
- Practice/perform it by sorting speech sequences by length during the first training epoch.
What to know first
- convolutional neural networkA convolutional neural network is a neural-network architecture that processes structured inputs with convolutional operations, typically using learned local filters to capture patterns.
- LSTMA long short-term memory (LSTM) network is a recurrent neural-network architecture with gated memory cells that control information flow and model dependencies in sequential data.
- ReLUReLU is an activation function that maps an input x to the greater of x and zero.
Questions about curriculum learning
What is curriculum learning?
Curriculum learning is a training strategy that presents tasks or examples in an organized progression, typically from easier to more difficult cases.
Which Manning books explain curriculum learning?
Applied Reinforcement Learning and Sutskever's List.
What should I know before learning curriculum learning?
Manning books that teach curriculum learning usually introduce convolutional neural network, LSTM and ReLU first.
What kinds of curriculum learning are there?
Kinds of curriculum learning include SortaGrad curriculum learning.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

