# --------------------------
# A2C
# --------------------------
- name: rllib_learning_tests_a2c_tf
  group: RLlib tests
  working_dir: rllib_tests
  stable: false

  frequency: nightly
  team: rllib

  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 1gpu_16cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=a2c --framework=tf

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 1gpu_16cpus_gce.yaml

- name: rllib_learning_tests_a2c_torch
  group: RLlib tests
  working_dir: rllib_tests
  stable: false

  frequency: nightly
  team: rllib
  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 1gpu_16cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=a2c --framework=torch

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 1gpu_16cpus_gce.yaml

# --------------------------
# A3C
# --------------------------
- name: rllib_learning_tests_a3c_tf
  group: RLlib tests
  working_dir: rllib_tests
  stable: false

  frequency: nightly
  team: rllib

  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 32cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=a3c --framework=tf

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 32cpus_gce.yaml


# --------------------------
# APEX-DQN
# --------------------------
- name: rllib_learning_tests_apex_dqn_tf
  group: RLlib tests
  working_dir: rllib_tests

  # Marking as unstable since it's currently expected to fail.
  stable: false

  frequency: nightly
  team: rllib
  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 1gpu_24cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=apex --framework=tf

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 1gpu_24cpus_gce.yaml

- name: rllib_learning_tests_apex_dqn_torch
  group: RLlib tests
  working_dir: rllib_tests
  stable: false

  frequency: nightly
  team: rllib
  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 1gpu_24cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=apex --framework=torch

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 1gpu_24cpus_gce.yaml


# --------------------------
# DDPG
# --------------------------
- name: rllib_learning_tests_ddpg_tf
  group: RLlib tests
  working_dir: rllib_tests

  frequency: nightly
  stable: false
  team: rllib

  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 1gpu_16cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=ddpg --framework=tf

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 1gpu_16cpus_gce.yaml

- name: rllib_learning_tests_ddpg_torch
  group: RLlib tests
  working_dir: rllib_tests

  frequency: nightly
  stable: false
  team: rllib
  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 1gpu_16cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=ddpg --framework=torch

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 1gpu_16cpus_gce.yaml


# --------------------------
# ES
# --------------------------
- name: rllib_learning_tests_es_tf
  group: RLlib tests
  working_dir: rllib_tests
  stable: false

  frequency: nightly
  team: rllib

  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 2gpus_64cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=es --framework=tf

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 2gpus_64cpus_gce.yaml

- name: rllib_learning_tests_es_torch
  group: RLlib tests
  working_dir: rllib_tests
  stable: false

  frequency: nightly
  team: rllib

  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 2gpus_64cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=es --framework=torch

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 2gpus_64cpus_gce.yaml


# --------------------------
# SlateQ
# --------------------------
- name: rllib_learning_tests_slateq_tf
  group: RLlib tests
  working_dir: rllib_tests
  stable: false

  frequency: nightly
  team: rllib

  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 1gpu_16cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=slateq --framework=tf

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 1gpu_16cpus_gce.yaml

- name: rllib_learning_tests_slateq_torch
  group: RLlib tests
  working_dir: rllib_tests

  # Marking as unstable since it's currently expected to fail.
  stable: false

  frequency: nightly
  team: rllib
  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 1gpu_16cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=slateq --framework=torch

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 1gpu_16cpus_gce.yaml


# --------------------------
# TD3
# --------------------------
- name: rllib_learning_tests_td3_tf
  group: RLlib tests
  working_dir: rllib_tests
  stable: false

  frequency: nightly
  team: rllib

  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 1gpu_16cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=td3 --framework=tf

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 1gpu_16cpus_gce.yaml

- name: rllib_learning_tests_td3_torch
  group: RLlib tests
  working_dir: rllib_tests
  stable: false

  frequency: nightly
  team: rllib
  cluster:
    byod:
      type: gpu
      post_build_script: byod_rllib_test.sh
      runtime_env:
        - RLLIB_TEST_NO_JAX_IMPORT=1
        - LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/ray/.mujoco/mujoco210/bin
    cluster_compute: 1gpu_16cpus.yaml

  run:
    timeout: 18000
    script: python learning_tests/run.py --yaml-sub-dir=td3 --framework=torch

  alert: default

  variations:
    - __suffix__: aws
    - __suffix__: gce
      env: gce
      frequency: manual
      cluster:
        cluster_compute: 1gpu_16cpus_gce.yaml