wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-07-26 13:37:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] streaming minibatching for IMPALA (#3402)

Browse Source 
* mb impala

* fix

* paropt

* update

* cpu warn

* on cpu

* fix mb

* doc

* docs

* comment

* larger num

* early release

* remove grad clip

* only check loader count in multi gpu mode

* revert bad multigpu changes

* num sgd iter

* comment

* reuse optimizer

* add test

* par load test

* loosen test

* Update run_multi_node_tests.sh

* fix local mode

* Update agent.py
This commit is contained in:
Eric Liang
2018-12-19 02:23:29 -08:00
committed by GitHub
parent c4cba98c75
commit ffa6ee3ec8
8 changed files with 258 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/jenkins_tests/run_multi_node_tests.sh
+2 -2
View File
@@ -214,14 +214,14 @@ docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} $DOCKER_SHA \
--env CartPole-v0 \
--run IMPALA \
--stop '{"training_iteration": 2}' \
--config '{"num_gpus": 0, "num_workers": 2, "min_iter_time_s": 1, "num_parallel_data_loaders": 2, "replay_proportion": 1.0}'
--config '{"num_gpus": 0, "num_workers": 2, "min_iter_time_s": 1, "num_data_loader_buffers": 2, "replay_proportion": 1.0}'
docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
--env CartPole-v0 \
--run IMPALA \
--stop '{"training_iteration": 2}' \
--config '{"num_gpus": 0, "num_workers": 2, "min_iter_time_s": 1, "num_parallel_data_loaders": 2, "replay_proportion": 1.0, "model": {"use_lstm": true}}'
--config '{"num_gpus": 0, "num_workers": 2, "min_iter_time_s": 1, "num_data_loader_buffers": 2, "replay_proportion": 1.0, "model": {"use_lstm": true}}'
docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \