Workflow
Policy and Value Networks
Trainers
Concepts and Structure
Environment Customization
Best Practices and Tutorials
Logging
Scaling the Training Process
maze.core.agent_integration.external_core_env.
ExternalCoreEnvRewardAggregator
Reward aggregator for summing up rewards that come as iterables from external env. Scalar rewards are just passed through.
get_interfaces
No event interfaces required.
to_scalar_reward
Sum up reward if iterable, otherwise just pass through.