Pre-Release to try out

What's Changed

• Revert the init pool due to compiler error for windows by @rizkydiprasetya in #112
• use numpy instead of math by @rizkydiprasetya in #113
• Delete by @rizkydiprasetya in #114
• Hotfix main loop by @rizkydiprasetya in #119
• Model Improvements by @detlefarend in #116
• Fix due to new change observation and state by @rizkydiprasetya in #121
• Model Improvements(2) by @detlefarend in #126
• Feature/wrapper sb3 off policy by @rizkydiprasetya in #123
• Feature/test script for SB3 policy wrappers by @rizkydiprasetya in #134
• Property class "ScientificObject" and class "DataPlotting" by @steveyuwono in #139
• Feature/wrapper native sb3 policy for On-Policy by @rizkydiprasetya in #143
• Static method for gym spaces transformation by @steveyuwono in #147
• ReadTheDocs by @steveyuwono in #154
• Model Improvements(3) by @detlefarend in #128
• BGLP improvement by @steveyuwono in #165
• add auto testing documentation by @rizkydiprasetya in #166
• Revert "add auto testing documentation" by @rizkydiprasetya in #167
• add Howto 14 UR5 with SB3 Wrapper, update the environment by @rizkydiprasetya in #168
• remove dependency from torch on BGLP env by @steveyuwono in #171
• fix robotinhtm environment by @rizkydiprasetya in #174
• BGLP minor change by @steveyuwono in #176
• Documentation on Read the Docs by @steveyuwono in #159
• Bglp gt env update by @steveyuwono in #181
• add how to for robothtm env by @rizkydiprasetya in #183
• remove python 3.7 from the test by @rizkydiprasetya in #184
• Read the docs by @detlefarend in #182
• Model Improvements #4 by @detlefarend in #177
• Fix How to 13 and include how to 15 to the test by @rizkydiprasetya in #189
• Bugfix in class AFctBase by @detlefarend in #191
• fix Set.append() due to max() on empty by @rizkydiprasetya in #197
• PR, readme, contributing template by @rizkydiprasetya in #198
• Change the states by @rizkydiprasetya in #199
• Add dummy policy in pool and add test policy by @rizkydiprasetya in #200
• Model improvements5 by @detlefarend in #196
• RTD Documentation by @detlefarend in #190
• Wrapper Hyperopt by @steveyuwono in #193
• BGLP clean code assurance by @steveyuwono in #201
• cleaning the code by @rizkydiprasetya in #202
• update plot.py: Add errors and exceptions, if p_printing is None and clean code assurance. by @steveyuwono in #205
• Read the docs by @detlefarend in #208
• License changed to Apache 2.0 by @detlefarend in #204
• Model improvements6 by @detlefarend in #206
• Import ur env by @budiatmadjajaWill in #209
• Read the docs by @detlefarend in #213
• Update documentation images by @budiatmadjajaWill in #214
• Added the official/legal logo by @detlefarend in #215
• Model Based Reinforcement Learning by @rizkydiprasetya in #216
• init by @rizkydiprasetya in #217
• Edit readme by @rizkydiprasetya in #218
• add readthedocs link by @rizkydiprasetya in #219
• add auto deploy docker by @rizkydiprasetya in #220
• Documentation by @detlefarend in #221
• Implementation of Multi geometry robot environment by @rizkydiprasetya in #225
• Model Improvements 7 by @detlefarend in #211
• RTD: Review and clean up by @detlefarend in #228
• Correction setup.cfg by @detlefarend in #229

Full Changelog: v0.5.0...v0.8.0

Pre-Release for internal purposes

What's Changed

• Implementation of A2C on top of MLPro structure by @rizkydiprasetya in #16
• Merging new Buffer Implementation by @rizkydiprasetya in #20
• A2C Implementation by @rizkydiprasetya in #23
• SARBuffer with random sampling implementation by @rizkydiprasetya in #25
• Fix Howto due to the changes in SARBuffer Implementation by @rizkydiprasetya in #26
• Check Review Mechanism by @rizkydiprasetya in #27
• Revert "Check Review Mechanism" by @rizkydiprasetya in #30
• test review mechanism again by @rizkydiprasetya in #31
• Revert "test review mechanism again" by @rizkydiprasetya in #32
• test review mechanism by @rizkydiprasetya in #33
• Revert "test review mechanism" by @rizkydiprasetya in #34
• Contact data changed in both setup files by @detlefarend in #55
• Further improvement on Buffer and BufferElement Class by @rizkydiprasetya in #35
• Test Issue by @rizkydiprasetya in #57
• Revert "Test Issue" by @rizkydiprasetya in #58
• debug bglp_localinterpolation scenario by @steveyuwono in #62
• Dev ur5 by @budiatmadjajaWill in #61
• Fixing SARBuffer Mechanism by @rizkydiprasetya in #64
• Bf big data extension by @detlefarend in #66
• Update WrEnvGym and WrEnvPZoo class following big data extension by @steveyuwono in #67
• A2C Implementation for Discrete Action by @rizkydiprasetya in #69
• Howto Train UR5 Robot environment with A2C Algorithm by @budiatmadjajaWill in #68
• SAC Implementation by @rizkydiprasetya in #72
• Add automated test on pull request by @rizkydiprasetya in #73
• Update python-app.yml by @rizkydiprasetya in #74
• Edit Readme by @rizkydiprasetya in #80
• Added PrioritizedBuffer, PrioritizedBufferElement, SegmentTree by @budiatmadjajaWill in #84
• Quick Fix on SAC Algorithm by @rizkydiprasetya in #86
• Restructure pool by @rizkydiprasetya in #87
• Test Script for SARBuffer and fix on SAC import statement by @budiatmadjajaWill in #90
• Read the docs by @steveyuwono in #96
• Model improvements by @detlefarend in #95
• Agent Adaptation by @detlefarend in #97
• Implementation of SB3 Wrapper for On-Policy Algorithm Only by @rizkydiprasetya in #93
• BGLP Env. Improvement and SciUI RL by @steveyuwono in #104
• Agent Adaptation(2) by @detlefarend in #107
• Updated setup files and created a build by @detlefarend in #109

Full Changelog: https://github.com/fhswf/MLPro/commits/v0.5.0