From b8a9e3f1064c6f8d754884fd9c75e0b2f88df4d6 Mon Sep 17 00:00:00 2001 From: Eric Liang Date: Tue, 1 Jan 2019 12:01:27 +0800 Subject: [PATCH] [rllib] Remove uses of sgd_stepsize => lr (#3667) * lr * Update example-evolution-strategies.rst --- doc/source/example-evolution-strategies.rst | 2 +- doc/source/rllib-training.rst | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/doc/source/example-evolution-strategies.rst b/doc/source/example-evolution-strategies.rst index d048d261f..38268bb46 100644 --- a/doc/source/example-evolution-strategies.rst +++ b/doc/source/example-evolution-strategies.rst @@ -28,7 +28,7 @@ To train a policy on a cluster (e.g., using 900 workers), run the following. --env=Humanoid-v1 \ --run=ES \ --redis-address= \ - --config='{"num_workers": 900, "episodes_per_batch": 10000, "timesteps_per_batch": 100000}' + --config='{"num_workers": 900, "episodes_per_batch": 10000, "train_batch_size": 100000}' At the heart of this example, we define a ``Worker`` class. These workers have a method ``do_rollouts``, which will be used to perform simulate randomly diff --git a/doc/source/rllib-training.rst b/doc/source/rllib-training.rst index 291ae0462..cc73ec086 100644 --- a/doc/source/rllib-training.rst +++ b/doc/source/rllib-training.rst @@ -156,7 +156,7 @@ All RLlib agents are compatible with the `Tune API `__. This en "config": { "num_gpus": 0, "num_workers": 1, - "sgd_stepsize": tune.grid_search([0.01, 0.001, 0.0001]), + "lr": tune.grid_search([0.01, 0.001, 0.0001]), }, }, }) @@ -170,10 +170,10 @@ Tune will schedule the trials to run in parallel on your Ray cluster: Resources requested: 4/4 CPUs, 0/0 GPUs Result logdir: ~/ray_results/my_experiment PENDING trials: - - PPO_CartPole-v0_2_sgd_stepsize=0.0001: PENDING + - PPO_CartPole-v0_2_lr=0.0001: PENDING RUNNING trials: - - PPO_CartPole-v0_0_sgd_stepsize=0.01: RUNNING [pid=21940], 16 s, 4013 ts, 22 rew - - PPO_CartPole-v0_1_sgd_stepsize=0.001: RUNNING [pid=21942], 27 s, 8111 ts, 54.7 rew + - PPO_CartPole-v0_0_lr=0.01: RUNNING [pid=21940], 16 s, 4013 ts, 22 rew + - PPO_CartPole-v0_1_lr=0.001: RUNNING [pid=21942], 27 s, 8111 ts, 54.7 rew Accessing Policy State ~~~~~~~~~~~~~~~~~~~~~~