Exploration with Parameter Space Noise (#4048)

*  enable parameter space noise for exploration

*  enable parameter space noise for exploration

*  yapf formatted

*  remove the usage of scipy softmax avialable in the latest version only

*  enable subclass that has no parameter_noise in the config

*  run user specified callbacks and test parameter space noise in multi node setting

*  formatted by yapf

* Update dqn.py

* lint
This commit is contained in:
Jones Wong
2019-02-21 14:35:18 +08:00
committed by Eric Liang
parent bcd5af78c7
commit 3ac8fd7ee8
6 changed files with 234 additions and 12 deletions
@@ -259,6 +259,14 @@ docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} $DOCKER_SHA \
--stop '{"training_iteration": 2}' \
--config '{"num_workers": 2, "optimizer": {"num_replay_buffer_shards": 1}, "learning_starts": 100, "min_iter_time_s": 1}'
docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
--env Pendulum-v0 \
--run APEX_DDPG \
--ray-num-cpus 8 \
--stop '{"training_iteration": 2}' \
--config '{"num_workers": 2, "optimizer": {"num_replay_buffer_shards": 1}, "learning_starts": 100, "min_iter_time_s": 1, "batch_mode": "complete_episodes", "parameter_noise": true}'
docker run --rm --shm-size=${SHM_SIZE} --memory=${MEMORY_SIZE} $DOCKER_SHA \
python /ray/python/ray/rllib/train.py \
--env CartPole-v0 \