Sync with upstream 0.2.0 release

Author: Kojoley

.travis.yml

@@ -1,52 +1,42 @@
+language: sh
+script: ./build.sh
+os: 
+    - linux
+    - windows
+    - osx
 env:
-  global:
-    - REPO_DIR=.
-    - BUILD_COMMIT=$TRAVIS_COMMIT
-    - PLAT=x86_64
-
-install: 
-  - git clone https://github.com/matthew-brett/multibuild && cd multibuild && git checkout 254ad28 && cd ..
-  - . multibuild/common_utils.sh
-  - . multibuild/travis_steps.sh
-  - before_install 
-  - build_wheel $REPO_DIR $PLAT
-script: 
-  - install_run $PLAT
-
-after_success:
-  - ./deploy.sh
-
-    
+    - PY_VER=3.6
+    - PY_VER=3.7
+    - PY_VER=3.5
+osx_image: xcode8.3
 matrix:
-  include:
+    exclude:
+        os: windows
+        env: PY_VER=3.5
+deploy:
+  provider: s3
+  access_key_id: AKIAIR7X3BP26ZWUNFPA
+  skip_cleanup: true
+  secret_access_key:
+    secure: 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
+  bucket: games-wheels
+  local-dir: wheelhouse
+  upload-dir: atari-py/$TRAVIS_TAG
+  acl: public_read
+  on:
+    repo: openai/atari-py
+    tags: true
 
-    - os: linux
-      env:
-        - MB_PYTHON_VERSION=3.5
-    
-    - os: linux
-      env:
-        - MB_PYTHON_VERSION=3.6
- 
-    - os: linux
-      env:
-        - MB_PYTHON_VERSION=3.7
-
-
-    - os: osx
-      osx_image: xcode8.3
-      env:
-        - MB_PYTHON_VERSION=3.5
-        - DEPLOY_SDIST=true
- 
-    - os: osx
-      osx_image: xcode8.3
-      env:
-        - MB_PYTHON_VERSION=3.6
- 
-    - os: osx
-      osx_image: xcode8.3
-      env:
-        - MB_PYTHON_VERSION=3.7
- 
- 
+jobs:
+  # this extra stage is due to Travis bug that prevets deploying to pypi from windows or usage of 
+  # secret env variables on windows. Instead of doing either, we are deploying to s3 first, and
+  # then using a separate stage to download files from s3 and deploy them to pypi. 
+  include:
+   - stage: "Deploy to PyPI"
+     script: ./deploy_to_pypi.sh
+     env:
+        - TWINE_USERNAME=peterz-openai
+        - AWS_ACCESS_KEY_ID=AKIAIR7X3BP26ZWUNFPA
+        - AWS_DEFAULT_REGION=us-west-2
+        - secure: "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"
+        - secure: "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"

ChangeLog

@@ -1,23 +1,119 @@
-(Contents from [https://github.com/bbitmaster/ale_python_interface](https://github.com/bbitmaster/ale_python_interface))
+[![Build Status](https://travis-ci.org/mgbellemare/Arcade-Learning-Environment.svg?branch=master)](https://travis-ci.org/mgbellemare/Arcade-Learning-Environment)
 
 <img align="right" src="doc/manual/figures/ale.gif" width=50>
 
-# Arcade-Learning-Environment
+# The Arcade Learning Environment
 
-The Arcade Learning Environment (ALE) -- a platform for AI research.
+The Arcade Learning Environment (ALE) is a simple object-oriented framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games. It is built on top of the Atari 2600 emulator [Stella](https://stella-emu.github.io/) and separates the details of emulation from agent design. This [video](https://www.youtube.com/watch?v=nzUiEkasXZI) depicts over 50 games currently supported in the ALE.
 
-For more details and installation instructions, see the [website](http://www.arcadelearningenvironment.org) and [manual](doc/manual/manual.pdf). To ask questions and discuss, please join the [ALE-users group](https://groups.google.com/forum/#!forum/arcade-learning-environment).
+For an overview of our goals for the ALE read [The Arcade Learning Environment: An Evaluation Platform for General Agents](http://www.jair.org/papers/paper3912.html). If you use ALE in your research, we ask that you please cite this paper in reference to the environment (BibTeX entry at the end of this document). Also, if you have any questions or comments about the ALE, please contact us through our [mailing list](https://groups.google.com/forum/#!forum/arcade-learning-environment).
 
-## Citing ALE
 
-If ALE helps in your research, please cite the following:
+Feedback and suggestions are welcome and may be addressed to any active member of the ALE team.
 
-    @article{bellemare13arcade,
-      author = {{Bellemare}, M.~G. and {Naddaf}, Y. and {Veness}, J. and {Bowling}, M.},
-      title = {The Arcade Learning Environment: An Evaluation Platform for General Agents},
-      journal = {Journal of Artificial Intelligence Research},
-      year = "2013",
-      month = "jun",
-      volume = "47",
-      pages = "253--279",
-    }
+### Features
+- Object-oriented framework with support to add agents and games.
+- Emulation core uncoupled from rendering and sound generation modules for fast emulation with minimal library dependencies.
+- Automatic extraction of game score and end-of-game signal for more than 50 Atari 2600 games.
+- Multi-platform code (compiled and tested under OS X and several Linux distributions, with Cygwin support).
+- Communication between agents and emulation core can be accomplished through pipes, allowing for cross-language development (sample Java code included).
+- Python development is supported through ctypes.
+- Agents programmed in C++ have access to all features in the ALE.
+- Visualization tools.
+
+## Quick start
+
+
+Install main dependences:
+```
+sudo apt-get install libsdl1.2-dev libsdl-gfx1.2-dev libsdl-image1.2-dev cmake
+```
+
+Compilation:
+
+```
+$ mkdir build && cd build
+$ cmake -DUSE_SDL=ON -DUSE_RLGLUE=OFF -DBUILD_EXAMPLES=ON ..
+$ make -j 4
+```
+
+To install python module:
+
+```
+$ pip install .
+or
+$ pip install --user .
+```
+
+Getting the ALE to work on Visual Studio requires a bit of extra wrangling. You may wish to use IslandMan93's [Visual Studio port of the ALE.](https://github.com/Islandman93/Arcade-Learning-Environment)
+
+For more details and installation instructions, see the [manual](doc/manual/manual.pdf). To ask questions and discuss, please join the [ALE-users group](https://groups.google.com/forum/#!forum/arcade-learning-environment).
+
+## ALE releases
+
+Releases before v.0.5 are available for download in our previous [website](http://www.arcadelearningenvironment.org/). For the latest releases, please check our releases [page](https://github.com/mgbellemare/Arcade-Learning-Environment/releases).
+
+## List of command-line parameters
+
+Execute ./ale -help for more details; alternatively, see documentation 
+available at http://www.arcadelearningenvironment.org.
+
+```
+-random_seed [n] -- sets the random seed; defaults to the current time
+
+-game_controller [fifo|fifo_named] -- specifies how agents interact
+  with the ALE; see Java agent documentation for details
+
+-config [file] -- specifies a configuration file, from which additional 
+  parameters are read
+
+-run_length_encoding [false|true] -- determine whether run-length encoding is
+  used to send data over pipes; irrelevant when an internal agent is 
+  being used
+
+-max_num_frames_per_episode [n] -- sets the maximum number of frames per
+  episode. Once this number is reached, a new episode will start. Currently
+  implemented for all agents when using pipes (fifo/fifo_named) 
+
+-max_num_frames [n] -- sets the maximum number of frames (independent of how 
+  many episodes are played)
+```
+
+
+## Citing The Arcade Learning Environment
+
+
+If you use the ALE in your research, we ask that you please cite the following.
+
+*M. G. Bellemare, Y. Naddaf, J. Veness and M. Bowling. The Arcade Learning Environment: An Evaluation Platform for General Agents, Journal of Artificial Intelligence Research, Volume 47, pages 253-279, 2013.*
+
+In BibTeX format:
+
+```
+@Article{bellemare13arcade,
+  author = {{Bellemare}, M.~G. and {Naddaf}, Y. and {Veness}, J. and {Bowling}, M.},
+  title = {The Arcade Learning Environment: An Evaluation Platform for General Agents},
+  journal = {Journal of Artificial Intelligence Research},
+  year = "2013",
+  month = "jun",
+  volume = "47",
+  pages = "253--279",
+}
+```
+
+
+If you use the ALE with sticky actions (flag `repeat_action_probability`), or if you use the different game flavours (mode and difficulty switches), we ask you that you also cite the following:
+
+*M. C. Machado, M. G. Bellemare, E. Talvitie, J. Veness, M. J. Hausknecht, M. Bowling. Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents,  CoRR abs/1709.06009, 2017.*
+
+In BibTex format:
+
+```
+@Article{machado17arcade,
+  author = {Marlos C. Machado and Marc G. Bellemare and Erik Talvitie and Joel Veness and Matthew J. Hausknecht and Michael Bowling},
+  title = {Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents},
+  journal = {CoRR},
+  volume = {abs/1709.06009},
+  year = {2017}
+}
+```

Makefile

@@ -27,9 +27,25 @@ extern "C" {
   SYMBOL_EXPORT int act(ALEInterface *ale,int action){return ale->act((Action)action);}
   SYMBOL_EXPORT bool game_over(ALEInterface *ale){return ale->game_over();}
   SYMBOL_EXPORT void reset_game(ALEInterface *ale){ale->reset_game();}
+  SYMBOL_EXPORT void getAvailableModes(ALEInterface *ale,int *availableModes) {
+    ModeVect modes_vect = ale->getAvailableModes();
+    for(unsigned int i = 0; i < ale->getAvailableModes().size(); i++){
+      availableModes[i] = modes_vect[i];
+    }
+  }
+  SYMBOL_EXPORT int getAvailableModesSize(ALEInterface *ale) {return ale->getAvailableModes().size();}
+  SYMBOL_EXPORT void setMode(ALEInterface *ale, int mode) {ale->setMode(mode);}
+  SYMBOL_EXPORT void getAvailableDifficulties(ALEInterface *ale,int *availableDifficulties) {
+    DifficultyVect difficulties_vect = ale->getAvailableDifficulties();
+    for(unsigned int i = 0; i < ale->getAvailableDifficulties().size(); i++){
+      availableDifficulties[i] = difficulties_vect[i];
+    }
+  }
+  SYMBOL_EXPORT int getAvailableDifficultiesSize(ALEInterface *ale) {return ale->getAvailableDifficulties().size();}
+  SYMBOL_EXPORT void setDifficulty(ALEInterface *ale, int difficulty) {ale->setDifficulty(difficulty);}
   SYMBOL_EXPORT void getLegalActionSet(ALEInterface *ale,int *actions){
     ActionVect action_vect = ale->getLegalActionSet();
-    for(unsigned int i = 0;i < ale->getLegalActionSet().size();i++){
+    for(unsigned int i = 0; i < ale->getLegalActionSet().size(); i++){
       actions[i] = action_vect[i];
     }
   }
@@ -65,9 +81,10 @@ extern "C" {
     size_t screen_size = w*h;
     pixel_t *ale_screen_data = ale->getScreen().getArray();
 
-    ale->theOSystem->colourPalette().applyPaletteRGB(output_buffer, ale_screen_data, screen_size);
+    ale->theOSystem->colourPalette().applyPaletteRGB(output_buffer, ale_screen_data, screen_size );
   }
 
+
   SYMBOL_EXPORT void getScreenRGB2(ALEInterface *ale, unsigned char *output_buffer){
     size_t w = ale->getScreen().width();
     size_t h = ale->getScreen().height();
@@ -83,6 +100,7 @@ extern "C" {
     }
   }
 
+
   SYMBOL_EXPORT void getScreenGrayscale(ALEInterface *ale, unsigned char *output_buffer){
     size_t w = ale->getScreen().width();
     size_t h = ale->getScreen().height();