wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-08-16 11:27:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] Misc fixes, A2C (#2679)

Browse Source 
A bunch of minor rllib fixes:

pull in latest baselines atari wrapper changes (and use deepmind wrapper by default)
move reward clipping to policy evaluator
add a2c variant of a3c
reduce vision network fc layer size to 256 units
switch to 84x84 images
doc tweaks
print timesteps in tune status
This commit is contained in:
Eric Liang
2018-08-20 15:28:03 -07:00
committed by GitHub
parent 880ef1bd21
commit fbe6c59f72
34 changed files with 220 additions and 129 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/jenkins_tests/run_multi_node_tests.sh
+11 -4
View File
@@ -16,7 +16,14 @@ docker run -e "RAY_USE_XRAY=1" --rm --shm-size=10G --memory=10G $DOCKER_SHA \
--env PongDeterministic-v0 \
--run A3C \
--stop '{"training_iteration": 2}' \
--config '{"num_workers": 16}'
--config '{"num_workers": 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-v0 \
--run A2C \
--stop '{"training_iteration": 2}' \
--config '{"num_workers": 2}'
docker run -e "RAY_USE_XRAY=1" --rm --shm-size=10G --memory=10G $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
@@ -51,14 +58,14 @@ docker run -e "RAY_USE_XRAY=1" --rm --shm-size=10G --memory=10G $DOCKER_SHA \
--env Pendulum-v0 \
--run ES \
--stop '{"training_iteration": 2}' \
--config '{"stepsize": 0.01, "episodes_per_batch": 20, "timesteps_per_batch": 100}'
--config '{"stepsize": 0.01, "episodes_per_batch": 20, "timesteps_per_batch": 100, "num_workers": 2}'
docker run -e "RAY_USE_XRAY=1" --rm --shm-size=10G --memory=10G $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
--env Pong-v0 \
--run ES \
--stop '{"training_iteration": 2}' \
--config '{"stepsize": 0.01, "episodes_per_batch": 20, "timesteps_per_batch": 100}'
--config '{"stepsize": 0.01, "episodes_per_batch": 20, "timesteps_per_batch": 100, "num_workers": 2}'
docker run -e "RAY_USE_XRAY=1" --rm --shm-size=10G --memory=10G $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
@@ -276,7 +283,7 @@ docker run -e "RAY_USE_XRAY=1" --rm --shm-size=10G --memory=10G $DOCKER_SHA \
--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}}'
--config '{"num_workers": 2, "use_pytorch": true, "model": {"use_lstm": false, "grayscale": true, "zero_mean": false, "dim": 84, "channel_major": true}, "preprocessor_pref": "rllib"}'
docker run -e "RAY_USE_XRAY=1" --rm --shm-size=10G --memory=10G $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \