port other changes from aws#1618

Author: laurenyu

src/sagemaker/rl/estimator.py

@@ -69,7 +69,7 @@ class RLEstimator(Framework):
 
     COACH_LATEST_VERSION_TF = "0.11.1"
     COACH_LATEST_VERSION_MXNET = "0.11.0"
-    RAY_LATEST_VERSION = "0.6.5"
+    RAY_LATEST_VERSION = "0.8.5"
 
     def __init__(
         self,

tests/data/ray_cartpole/train_ray.py

@@ -5,12 +5,12 @@
 from ray.tune.logger import pretty_print
 
 # Based on https://github.com/ray-project/ray/blob/master/doc/source/rllib-training.rst#python-api
-ray.init(log_to_driver=False)
+ray.init(log_to_driver=False, webui_host="127.0.0.1")
 config = ppo.DEFAULT_CONFIG.copy()
 config["num_gpus"] = int(os.environ.get("SM_NUM_GPUS", 0))
 checkpoint_dir = os.environ.get("SM_MODEL_DIR", "/Users/nadzeya/gym")
 config["num_workers"] = 1
-agent = ppo.PPOAgent(config=config, env="CartPole-v0")
+agent = ppo.PPOTrainer(config=config, env="CartPole-v0")
 
 # Can optionally call agent.restore(path) to load a checkpoint.