Skip to content

Latest commit

 

History

History
27 lines (26 loc) · 760 Bytes

ROADMAP.md

File metadata and controls

27 lines (26 loc) · 760 Bytes

Roadmap

  1. RNN policies
    • Extend configurability
    • Allow recurrent baselines
    • More RNN modules, incl Transformer
  2. Reward estimation extensions
    • Auxiliary losses
    • Curiosity
    • Imitation learning
    • Distributional perspective
  3. State/action modeling
    • Sequence states/actions
    • State-dependent actions
    • Conditional/hierarchical actions
  4. Memory architecture
    • Optimize retrieval of sequences
    • Use TensorArray
    • Improve other limitations
  5. CARLA environment
    • Docs and assertions
    • World's map loading (e.g. random, specific, etc.)
    • Weather support
    • Pretraining and Free play (e.g. for data collection)
    • State space with a temporal component.
    • ...
  6. To be determined...