wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-08-08 11:25:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] Add debug info back to PPO and fix optimizer compatibility (#2366)

Browse Source
This commit is contained in:
Eric Liang
2018-07-12 19:22:46 +02:00
committed by Richard Liaw
parent 8ea926c266
commit b316afeb43
14 changed files with 122 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/jenkins_tests/run_multi_node_tests.sh
+9 -2
View File
@@ -25,6 +25,13 @@ docker run --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": {"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 '{"simple_optimizer": true, "model": {"use_lstm": true}}'
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
--env CartPole-v1 \
@@ -140,7 +147,7 @@ docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
--env CartPole-v0 \
--run PG \
--stop '{"training_iteration": 2}' \
--config '{"sample_batch_size": 500, "num_workers": 1, "num_envs": 10}'
--config '{"sample_batch_size": 500, "num_workers": 1, "num_envs_per_worker": 10}'
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
@@ -233,7 +240,7 @@ 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 /ray/python/ray/rllib/examples/multiagent_cartpole.py --num-iters=2
python $ROOT_DIR/multi_node_docker_test.py \
--docker-image=$DOCKER_SHA \