Once the trained policy has been trained, it can be deployed in all the supported as well as custom environments. Setting the task as GRID-Isaac-CustomRL-v0 and specifying the environment in the env.yaml enables users to use the trained policy in diverse environments. A sample agent.yaml file for inference is shown below: 
- rsl_rl_agent:
    type: "rsl_rl"
    mode: "play"
    config: 
      resume: false
      video: false
      video_length: 200
      video_interval: 2000
      empirical_normalization: false
      experiment_name: "my_experiment_name"
      load_run: .*
      load_checkpoint: model.*