add cart pole rl env

[matafela]

Description

Add cart pole rl env.

example: python embodichain/agents/rl/train.py --config configs/agents/rl/basic/cart_pole/train_config.json

TODO:

• Fix the problem that robots in the simulator all appear to be black.
• Upload cart pole robot urdf.

Type of change

• Enhancement (non-breaking change which improves an existing functionality)

Screenshots

ep198_main_cam_allenvs.mp4

Checklist

• I have run the black . command to format the code base.
• I have made corresponding changes to the documentation
• I have added tests that prove my fix is effective or that my feature works
• Dependencies have been updated, if applicable.

[Copilot]

Pull request overview

This draft PR adds a CartPole reinforcement learning environment to the embodichain framework. The implementation follows the existing pattern established by the PushCubeRL environment, introducing a new task where an agent must balance a pole on a movable cart by controlling the cart's position.

Changes:

• New CartPole RL environment class with success/failure conditions based on pole angle and velocity
• Optional goal_pose handling in RLEnv base class to support tasks without explicit goal positions
• New pole_upward reward function to encourage keeping the pole upright
• Configuration files for training and environment setup

Reviewed changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated 7 comments.

Show a summary per file

File	Description
embodichain/lab/gym/envs/tasks/rl/cart_pole.py	Implements CartPoleEnv with pole balancing logic, success criteria (angle < 0.05, velocity < 0.1), and truncation when pole falls beyond π/2 radians
embodichain/lab/gym/envs/rl_env.py	Makes goal_pose optional in info dictionary by checking for existence before adding, supporting tasks without explicit goal positions
embodichain/lab/gym/envs/managers/rewards.py	Adds pole_upward reward function that rewards keeping pole angle close to vertical (0 radians)
embodichain/lab/gym/envs/init.py	Imports and registers CartPoleEnv for use in the framework
configs/agents/rl/cart_pole/train_config.json	PPO training configuration with hyperparameters, camera settings, and wandb integration
configs/agents/rl/cart_pole/gym_config.json	Environment configuration including robot URDF path, joint parameters, observations, rewards, and control settings

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.