mirror of
https://github.com/vale981/ray
synced 2025-03-08 19:41:38 -05:00
5a50e0e1d7
* fix yaml bug * add ext agent * gpus * update * tuning * docs * Sun Oct 15 21:09:25 PDT 2017 * lint * update * Sun Oct 15 22:39:55 PDT 2017 * Sun Oct 15 22:40:17 PDT 2017 * Sun Oct 15 22:43:06 PDT 2017 * Sun Oct 15 22:46:06 PDT 2017 * Sun Oct 15 22:46:21 PDT 2017 * Sun Oct 15 22:48:11 PDT 2017 * Sun Oct 15 22:48:44 PDT 2017 * Sun Oct 15 22:49:23 PDT 2017 * Sun Oct 15 22:50:21 PDT 2017 * Sun Oct 15 22:53:00 PDT 2017 * Sun Oct 15 22:53:34 PDT 2017 * Sun Oct 15 22:54:33 PDT 2017 * Sun Oct 15 22:54:50 PDT 2017 * Sun Oct 15 22:55:20 PDT 2017 * Sun Oct 15 22:56:56 PDT 2017 * Sun Oct 15 22:59:03 PDT 2017 * fix * Update tune_mnist_ray.py * remove script trial * fix * reorder * fix ex * py2 support * upd * comments * comments * cleanup readme * fix trial * annotate * Update rllib.rst
122 lines
4.7 KiB
Bash
Executable file
122 lines
4.7 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
|
|
|
|
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
|
|
|
|
# Test that the example applications run.
|
|
|
|
# docker run --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
# python /ray/examples/lbfgs/driver.py
|
|
|
|
# docker run --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
# python /ray/examples/rl_pong/driver.py \
|
|
# --iterations=3
|
|
|
|
# docker run --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
# python /ray/examples/hyperopt/hyperopt_simple.py
|
|
|
|
# docker run --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
# python /ray/examples/hyperopt/hyperopt_adaptive.py
|
|
|
|
docker run --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env PongDeterministic-v0 \
|
|
--alg A3C \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"num_workers": 16}'
|
|
|
|
docker run --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v1 \
|
|
--alg 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 --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v1 \
|
|
--alg 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 --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env Pendulum-v0 \
|
|
--alg ES \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"stepsize": 0.01}'
|
|
|
|
docker run --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v0 \
|
|
--alg A3C \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"use_lstm": false}'
|
|
|
|
docker run --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env CartPole-v0 \
|
|
--alg 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 --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env PongDeterministic-v4 \
|
|
--alg 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 --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/train.py \
|
|
--env MontezumaRevenge-v0 \
|
|
--alg 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 --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/rllib/test/test_checkpoint_restore.py
|
|
|
|
docker run --shm-size=10G --memory=10G $DOCKER_SHA \
|
|
python /ray/python/ray/tune/tune.py \
|
|
--env mnist \
|
|
--stop '{"training_iteration": 2}' \
|
|
--config '{"script_file_path": "/ray/python/ray/tune/examples/tune_mnist_ray.py", "activation": "relu"}'
|