mirror of
https://github.com/vale981/ray
synced 2025-03-10 05:16:49 -04:00
1251abf0d1
* wip * cls * re * wip * wip * a3c working * torch support * pg works * lint * rm v2 * consumer id * clean up pg * clean up more * fix python 2.7 * tf session management * docs * dqn wip * fix compile * dqn * apex runs * up * impotrs * ddpg * quotes * fix tests * fix last r * fix tests * lint * pass checkpoint restore * kwar * nits * policy graph * fix yapf * com * class * pyt * vectorization * update * test cpe * unit test * fix ddpg2 * changes * wip * args * faster test * common * fix * add alg option * batch mode and policy serving * multi serving test * todo * wip * serving test * doc async env * num envs * comments * thread * remove init hook * update * fix ppo * comments1 * fix * updates * add jenkins tests * fix * fix pytorch * fix * fixes * fix a3c policy * fix squeeze * fix trunc on apex * fix squeezing for real * update * remove horizon test for now * multiagent wip * update * fix race condition * fix ma * t * doc * st * wip * example * wip * working * cartpole * wip * batch wip * fix bug * make other_batches None default * working * debug * nit * warn * comments * fix ppo * fix obs filter * update * wip * tf * update * fix * cleanup * cleanup * spacing * model * fix * dqn * fix ddpg * doc * keep names * update * fix * com * docs * clarify model outputs * Update torch_policy_graph.py * fix obs filter * pass thru worker index * fix * rename * vlad torch comments * fix log action * debug name * fix lstm * remove unused ddpg net * remove conv net * revert lstm * cast * clean up * fix lstm check * move to end * fix sphinx * fix cmd * remove bad doc * clarify * copy * async sa * fix
246 lines
9.2 KiB
Bash
Executable file
246 lines
9.2 KiB
Bash
Executable file
#!/usr/bin/env bash
|
|
|
|
# Cause the script to exit if a single command fails.
|
|
set -e
|
|
|
|
# Show explicitly which commands are currently running.
|
|
set -x
|
|
|
|
ROOT_DIR=$(cd "$(dirname "${BASH_SOURCE:-$0}")"; pwd)
|
|
|
|
DOCKER_SHA=$($ROOT_DIR/../../build-docker.sh --output-sha --no-cache)
|
|
echo "Using Docker image" $DOCKER_SHA
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env PongDeterministic-v0 \
|
|
--run A3C \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"num_workers": 16}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v1 \
|
|
--run PPO \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"kl_coeff": 1.0, "num_sgd_iter": 10, "sgd_stepsize": 1e-4, "sgd_batchsize": 64, "timesteps_per_batch": 2000, "num_workers": 1, "model": {"free_log_std": true}}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v1 \
|
|
--run PPO \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"kl_coeff": 1.0, "num_sgd_iter": 10, "sgd_stepsize": 1e-4, "sgd_batchsize": 64, "timesteps_per_batch": 2000, "num_workers": 1, "use_gae": false}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env Pendulum-v0 \
|
|
--run ES \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"stepsize": 0.01, "episodes_per_batch": 20, "timesteps_per_batch": 100}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env Pong-v0 \
|
|
--run ES \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"stepsize": 0.01, "episodes_per_batch": 20, "timesteps_per_batch": 100}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v0 \
|
|
--run A3C \
|
|
--stop '{"training_iteration": 2}' \
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v0 \
|
|
--run DQN \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"lr": 1e-3, "schedule_max_timesteps": 100000, "exploration_fraction": 0.1, "exploration_final_eps": 0.02, "dueling": false, "hiddens": [], "model": {"fcnet_hiddens": [64], "fcnet_activation": "relu"}}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v0 \
|
|
--run DQN \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"num_workers": 2}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v0 \
|
|
--run APEX \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"num_workers": 2, "timesteps_per_iteration": 1000, "gpu": false}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env FrozenLake-v0 \
|
|
--run DQN \
|
|
--stop '{"training_iteration": 2}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env FrozenLake-v0 \
|
|
--run PPO \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"num_sgd_iter": 10, "sgd_batchsize": 64, "timesteps_per_batch": 1000, "num_workers": 1}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env PongDeterministic-v4 \
|
|
--run DQN \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"lr": 1e-4, "schedule_max_timesteps": 2000000, "buffer_size": 10000, "exploration_fraction": 0.1, "exploration_final_eps": 0.01, "sample_batch_size": 4, "learning_starts": 10000, "target_network_update_freq": 1000, "gamma": 0.99, "prioritized_replay": true}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env MontezumaRevenge-v0 \
|
|
--run PPO \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"kl_coeff": 1.0, "num_sgd_iter": 10, "sgd_stepsize": 1e-4, "sgd_batchsize": 64, "timesteps_per_batch": 2000, "num_workers": 1, "model": {"dim": 40, "conv_filters": [[16, [8, 8], 4], [32, [4, 4], 2], [512, [5, 5], 1]]}, "extra_frameskip": 4}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env PongDeterministic-v4 \
|
|
--run A3C \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"num_workers": 2, "use_pytorch": true, "model": {"use_lstm": false, "grayscale": true, "zero_mean": false, "dim": 80, "channel_major": true}}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v1 \
|
|
--run A3C \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"num_workers": 2, "use_pytorch": true}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v0 \
|
|
--run DQN \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"num_workers": 2}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v0 \
|
|
--run PG \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"batch_size": 500, "num_workers": 1}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v0 \
|
|
--run PG \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"batch_size": 500, "num_workers": 1, "num_envs": 10}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env Pong-v0 \
|
|
--run PG \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"batch_size": 500, "num_workers": 1}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env FrozenLake-v0 \
|
|
--run PG \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"batch_size": 500, "num_workers": 1}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env Pendulum-v0 \
|
|
--run DDPG \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"num_workers": 1}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env MountainCarContinuous-v0 \
|
|
--run DDPG \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"num_workers": 1}'
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
sh /ray/test/jenkins_tests/multi_node_tests/test_rllib_eval.sh
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/test/test_checkpoint_restore.py
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/test/test_common_policy_evaluator.py
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/test/test_serving_env.py
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/test/test_supported_spaces.py
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/tune/examples/tune_mnist_ray.py \
|
|
--smoke-test
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/tune/examples/pbt_example.py \
|
|
--smoke-test
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/tune/examples/hyperband_example.py \
|
|
--smoke-test
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/tune/examples/async_hyperband_example.py \
|
|
--smoke-test
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/tune/examples/tune_mnist_ray_hyperband.py \
|
|
--smoke-test
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/tune/examples/tune_mnist_async_hyperband.py \
|
|
--smoke-test
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/tune/examples/hyperopt_example.py \
|
|
--smoke-test
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/examples/legacy_multiagent/multiagent_mountaincar.py
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/examples/legacy_multiagent/multiagent_pendulum.py
|
|
|
|
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/examples/multiagent_cartpole.py
|
|
|
|
python $ROOT_DIR/multi_node_docker_test.py \
|
|
--docker-image=$DOCKER_SHA \
|
|
--num-nodes=5 \
|
|
--num-redis-shards=10 \
|
|
--test-script=/ray/test/jenkins_tests/multi_node_tests/test_0.py
|
|
|
|
python $ROOT_DIR/multi_node_docker_test.py \
|
|
--docker-image=$DOCKER_SHA \
|
|
--num-nodes=5 \
|
|
--num-redis-shards=5 \
|
|
--num-gpus=0,1,2,3,4 \
|
|
--num-drivers=7 \
|
|
--driver-locations=0,1,0,1,2,3,4 \
|
|
--test-script=/ray/test/jenkins_tests/multi_node_tests/remove_driver_test.py
|
|
|
|
python $ROOT_DIR/multi_node_docker_test.py \
|
|
--docker-image=$DOCKER_SHA \
|
|
--num-nodes=5 \
|
|
--num-redis-shards=2 \
|
|
--num-gpus=0,0,5,6,50 \
|
|
--num-drivers=100 \
|
|
--test-script=/ray/test/jenkins_tests/multi_node_tests/many_drivers_test.py
|
|
|
|
python $ROOT_DIR/multi_node_docker_test.py \
|
|
--docker-image=$DOCKER_SHA \
|
|
--num-nodes=1 \
|
|
--mem-size=60G \
|
|
--shm-size=60G \
|
|
--test-script=/ray/test/jenkins_tests/multi_node_tests/large_memory_test.py
|