wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-08-12 12:20:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] Workaround actor creation hang edge case for ape-X (#2661)

Browse Source 
* apex hang

* fix

* move pyt to end
This commit is contained in:
Eric Liang
2018-08-16 18:03:50 -07:00
committed by GitHub
parent 5f430da180
commit 6670880f03
3 changed files with 41 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/jenkins_tests/run_multi_node_tests.sh
+15 -15
View File
@@ -114,20 +114,6 @@ docker run -e "RAY_USE_XRAY=1" --rm --shm-size=10G --memory=10G $DOCKER_SHA \
--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]]}}'
docker run -e "RAY_USE_XRAY=1" --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 -e "RAY_USE_XRAY=1" --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 -e "RAY_USE_XRAY=1" --rm --shm-size=10G --memory=10G $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
--env CartPole-v1 \
@@ -285,6 +271,20 @@ docker run -e "RAY_USE_XRAY=1" --rm --shm-size=10G --memory=10G $DOCKER_SHA \
docker run -e "RAY_USE_XRAY=1" --rm --shm-size=10G --memory=10G $DOCKER_SHA \
python /ray/python/ray/rllib/examples/multiagent_two_trainers.py --num-iters=2
docker run -e "RAY_USE_XRAY=1" --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 -e "RAY_USE_XRAY=1" --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}'
python3 $ROOT_DIR/multi_node_docker_test.py \
--docker-image=$DOCKER_SHA \
--num-nodes=5 \
@@ -316,4 +316,4 @@ python3 $ROOT_DIR/multi_node_docker_test.py \
--mem-size=60G \
--shm-size=60G \
--use-raylet \
--test-script=/ray/test/jenkins_tests/multi_node_tests/large_memory_test.py
--test-script=/ray/test/jenkins_tests/multi_node_tests/large_memory_test.py