From 24ced808cd13d88402899c0fe013d9a5175a20e2 Mon Sep 17 00:00:00 2001
From: Jason McGhee <mcghee.j@gmail.com>
Date: Mon, 11 May 2020 12:41:21 -0700
Subject: [PATCH] Fix config key in docs for using PyTorch (#8300)

Docs improperly suggest using "torch" when the actual flag is called "use_pytorch"
---
 doc/source/rllib.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/doc/source/rllib.rst b/doc/source/rllib.rst
index 68e30cc13..cf8f440cf 100644
--- a/doc/source/rllib.rst
+++ b/doc/source/rllib.rst
@@ -37,7 +37,7 @@ Then, you can try out training in the following equivalent ways:
   from ray.rllib.agents.ppo import PPOTrainer
   tune.run(PPOTrainer, config={"env": "CartPole-v0"})  # "log_level": "INFO" for verbose,
                                                        # "eager": True for eager execution,
-                                                       # "torch": True for PyTorch
+                                                       # "use_pytorch": True for PyTorch
 
 Next, we'll cover three key concepts in RLlib: Policies, Samples, and Trainers.