wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-09-11 12:43:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] Refactor DQN to use an Evaluator abstraction (#1276)

Browse Source 
This introduces rllib.Evaluator and rllib.Optimizer classes. Optimizers encapsulate a particular distributed optimization strategy for RL. Evaluators encapsulate the model graph, and once implemented, any Optimizer may be "plugged in" to any algorithm that implements the Evaluator interface.
This commit is contained in:
Eric Liang
2017-12-06 17:51:57 -08:00
committed by GitHub
parent 044548bcff
commit 2d543b6e19
16 changed files with 694 additions and 805 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/jenkins_tests/run_multi_node_tests.sh
+7
View File
@@ -105,6 +105,13 @@ docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
--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 --rm --shm-size=10G --memory=10G $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
--env CartPole-v0 \
--run DQN \
--stop '{"training_iteration": 2}' \
--config '{"async_updates": true, "num_workers": 2}'
docker run --rm --shm-size=10G --memory=10G $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
--env FrozenLake-v0 \