Mava
Mava copied to clipboard
[FEATURE] Creating the executor for MADQN
Feature
As the first step to have the first MADQN system, the executor is created.
Proposal
The MAPPO design in jax/systems/mappo and its executor are modified for which :
-
FeedforwardExecutorSelectAction
is changed toFeedforwardExecutorSelectActionValueBased
-
PPONetworks
is changed toDQNNetworks
-
EpsilonScheduler
is added
Testing
Tests are same as MAPPO system_tests with additional tests:
- steps_counter
- epsilon scheduler
Definition of done
A precise outline for the feature to be considered fully implemented, i.e. done/complete. The executor is implemented and passes the tests.
Mandatory checklist before making a PR
- [ ] The success criteria laid down in āDefinition of doneā are met.
- [ ] Code is documented - docstrings for methods and classes, static types for arguments.
- [ ] Code is tested - unit, integration and/or functional tests are added.
- [ ] Documentation is updated - README, CONTRIBUTING, or other documentation.
- [ ] All functional tests are green.
- [ ] Link experiment/benchmarking after implementation (optional).