This is an automated email from the ASF dual-hosted git repository.
jxie pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git
The following commit(s) were added to refs/heads/master by this push:
new 005f677 setup.sh and fix visualization in dqn_run_test.py (#11051)
005f677 is described below
commit 005f67759fac7bcf451e31b42c30b6c6ca24586a
Author: Pedro Larroy <928489+lar...@users.noreply.github.com>
AuthorDate: Thu May 31 03:36:29 2018 +0900
setup.sh and fix visualization in dqn_run_test.py (#11051)
fix type error: type of action needs to be int
---
example/reinforcement-learning/dqn/README.md | Bin 2146 -> 2230 bytes
example/reinforcement-learning/dqn/dqn_run_test.py | 8 +++++---
example/reinforcement-learning/dqn/setup.sh | 7 ++++++-
3 files changed, 11 insertions(+), 4 deletions(-)
diff --git a/example/reinforcement-learning/dqn/README.md
b/example/reinforcement-learning/dqn/README.md
index fd32667..4547904 100644
Binary files a/example/reinforcement-learning/dqn/README.md and
b/example/reinforcement-learning/dqn/README.md differ
diff --git a/example/reinforcement-learning/dqn/dqn_run_test.py
b/example/reinforcement-learning/dqn/dqn_run_test.py
old mode 100644
new mode 100755
index 2abf273..e8f36b9
--- a/example/reinforcement-learning/dqn/dqn_run_test.py
+++ b/example/reinforcement-learning/dqn/dqn_run_test.py
@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
@@ -89,8 +91,8 @@ def calculate_avg_reward(game, qnet, test_steps=125000,
exploartion=0.05):
current_state = game.current_state()
state = nd.array(current_state.reshape((1,) +
current_state.shape),
ctx=qnet.ctx) / float(255.0)
- action = nd.argmax_channel(
- qnet.forward(is_train=False, data=state)[0]).asscalar()
+ action = int(nd.argmax_channel(
+ qnet.forward(is_train=False,
data=state)[0]).asscalar())
else:
action = npy_rng.randint(action_num)
@@ -120,7 +122,7 @@ def main():
help='Running Context. E.g `-c gpu` or `-c gpu1` or
`-c cpu`')
parser.add_argument('-e', '--epoch-range', required=False, type=str,
default='22',
help='Epochs to run testing. E.g `-e 0,80`, `-e
0,80,2`')
- parser.add_argument('-v', '--visualization', required=False, type=int,
default=0,
+ parser.add_argument('-v', '--visualization', action='store_true',
help='Visualize the runs.')
parser.add_argument('--symbol', required=False, type=str, default="nature",
help='type of network, nature or nips')
diff --git a/example/reinforcement-learning/dqn/setup.sh
b/example/reinforcement-learning/dqn/setup.sh
index 3fcfacb..3069fef 100755
--- a/example/reinforcement-learning/dqn/setup.sh
+++ b/example/reinforcement-learning/dqn/setup.sh
@@ -22,9 +22,14 @@ set -x
pip install opencv-python
pip install scipy
+pip install pygame
# Install arcade learning environment
-sudo apt-get install libsdl1.2-dev libsdl-gfx1.2-dev libsdl-image1.2-dev cmake
+if [[ "$OSTYPE" == "linux-gnu" ]]; then
+ sudo apt-get install libsdl1.2-dev libsdl-gfx1.2-dev libsdl-image1.2-dev
cmake
+elif [[ "$OSTYPE" == "darwin"* ]]; then
+ brew install sdl sdl_image sdl_mixer sdl_ttf portmidi
+fi
git clone g...@github.com:mgbellemare/Arcade-Learning-Environment.git || true
pushd .
cd Arcade-Learning-Environment
--
To stop receiving notification emails like this one, please contact
j...@apache.org.
