wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-07-16 11:21:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] Basic infrastructure for off-policy estimation (IS, WIS) (#3941)

Browse Source
This commit is contained in:
Eric Liang
2019-02-13 16:25:05 -08:00
committed by GitHub
parent 729d0b2825
commit 2dccf383dd
34 changed files with 549 additions and 131 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/jenkins_tests/run_multi_node_tests.sh
+9 -1
View File
@@ -251,12 +251,20 @@ docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} $DOCKER_SHA \
--ray-num-cpus 8 \
--stop '{"training_iteration": 2}' \
--config '{"num_workers": 2, "optimizer": {"num_replay_buffer_shards": 1}, "learning_starts": 100, "min_iter_time_s": 1}'
docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
--env CartPole-v0 \
--run MARWIL \
--stop '{"training_iteration": 2}' \
--config '{"input": "/ray/python/ray/rllib/test/data/cartpole_small", "learning_starts": 0}'
--config '{"input": "/ray/python/ray/rllib/test/data/cartpole_small", "learning_starts": 0, "input_evaluation": ["wis", "is"], "shuffle_buffer_size": 10}'
docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
--env CartPole-v0 \
--run DQN \
--stop '{"training_iteration": 2}' \
--config '{"input": "/ray/python/ray/rllib/test/data/cartpole_small", "learning_starts": 0, "input_evaluation": ["wis", "is"], "soft_q": true}'
docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} $DOCKER_SHA \
python /ray/python/ray/rllib/test/test_local.py