Welcome to l2rpn-baselines’s documentation!

In this documentation we expose first what is this package about and how to contribute, and then which baselines are already implemented in this package.

How to contribute

• Template: How to contribute to l2rpn baselines
  • Description
  • Implementation Example
• Do Nothing: a more concrete example the “do nothing” Baseline
  • Description
  • Implementation Example

Baseline already Available

• utils: Some utility functions and classes
  • Description
  • Focus on the training parameters
  • Focus on the architecture
  • Implementation Details
• DeepQSimple: A simple implementation of the Deep Q Learning
  • Description
  • Exported class
  • Other non exported class
• DoubleDuelingDQN: A example implementation of Double Duelling Deep Q Network
  • Description
  • Agent class
  • Configuration
  • Internal classes
• DuelQSimple: Double Duelling Deep Q Learning
  • Description
  • Exported class
  • Other non exported class
• ExpertAgent: A example implementation of using ExpertOpForGrid for empirical overflow solving
  • Description
  • Agent class

More advanced baselines

• DuelQLeapNet: D3QN with LeapNet
  • Description
  • Exported class
  • Other non exported class
• DoubleDuelingRDQN: A example implementation of Recurrent DoubleQ Network
  • Description
  • Agent class
  • Configuration
  • Internal classes
• LeapNetEncoded: D3QN on a state encoded by a leap net
  • Description
  • Exported class
  • Other non exported class

Deprecated baselines

• SAC: Soft Actor Critic
  • Description
  • Exported class
  • Other non exported class

Contributions

TODO

Indices and tables

• Index

• Module Index

• Search Page