Skip to content

Feature Roadmap: Gymnasium RL Environment and Examples #54

Description

@JacopoPan

SITL and perception-enabled reinforcement learning for real-world deployment

  • Wrap FTRT, headless, steppable simulation in aas-gym
  • Optimize the environment .reset() time
  • Conditional/AP mode startup to replace GYM_INIT_DURATION
  • offboard_control references from external topics bridged by ZeroMQ
  • observation space definition
  • multi-agent support (including mixed RL-scripted agents)

Metadata

Metadata

Assignees

Labels

enhancementNew feature or request

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions