# Heavy learning tests (Atari and HalfCheetah) for major algos. - name: learning_tests cluster: app_config: app_config.yaml compute_template: 8gpus_64cpus.yaml run: timeout: 14400 script: python learning_tests/run.py smoke_test: run: timeout: 1200 # 2-GPU learning tests (CartPole and RepeatAfterMeEnv) for major algos. - name: multi_gpu_learning_tests cluster: app_config: app_config.yaml compute_template: 8gpus_96cpus.yaml run: timeout: 7200 script: python multi_gpu_learning_tests/run.py # 2-GPU learning tests (StatelessCartPole) + use_lstm=True for major algos # (that support RNN models). - name: multi_gpu_with_lstm_learning_tests cluster: app_config: app_config.yaml compute_template: 8gpus_96cpus.yaml run: timeout: 7200 script: python multi_gpu_with_lstm_learning_tests/run.py # 2-GPU learning tests (StatelessCartPole) + use_attention=True for major # algos (that support RNN models). - name: multi_gpu_with_attention_learning_tests cluster: app_config: app_config.yaml compute_template: 8gpus_96cpus.yaml run: timeout: 7200 script: python multi_gpu_with_attention_learning_tests/run.py # We'll have these as per-PR tests soon. # - name: example_scripts_on_gpu_tests # cluster: # app_config: app_config.yaml # compute_template: 1gpu_4cpus.yaml # run: # timeout: 7200 # script: bash unit_gpu_tests/run.sh # IMPALA large machine stress tests (4x Atari). - name: stress_tests cluster: app_config: app_config.yaml compute_template: 4gpus_544_cpus.yaml run: timeout: 5400 prepare: python wait_cluster.py 6 600 script: python stress_tests/run_stress_tests.py smoke_test: run: timeout: 2000 # Tests that exercise auto-scaling and Anyscale connect. - name: connect_tests cluster: app_config: app_config.yaml compute_template: auto_scale.yaml run: use_connect: True timeout: 3000 script: python connect_tests/run_connect_tests.py # Nightly performance regression for popular algorithms. # These algorithms run nightly for pre-determined amount of time without # passing criteria. # Performance metrics, such as reward achieved and throughput, are then # collected and tracked over time. - name: performance_tests cluster: app_config: app_config.yaml compute_template: 12gpus_192cpus.yaml run: timeout: 7200 script: python performance_tests/run.py