wise-move merge requestshttps://git.uwaterloo.ca/wise-lab/wise-move/-/merge_requests2018-11-18T00:03:14-05:00https://git.uwaterloo.ca/wise-lab/wise-move/-/merge_requests/1update doc, scripts (from bitbucket)2018-11-18T00:03:14-05:00Ashish Gauravashish.gaurav@uwaterloo.caupdate doc, scripts (from bitbucket)https://git.uwaterloo.ca/wise-lab/wise-move/-/merge_requests/2Final test2018-11-18T04:41:29-05:00Jae Young Leejaeyoung.lee@uwaterloo.caFinal testJae Young Leejaeyoung.lee@uwaterloo.caJae Young Leejaeyoung.lee@uwaterloo.cahttps://git.uwaterloo.ca/wise-lab/wise-move/-/merge_requests/3Formatting2018-11-19T18:28:48-05:00Ashish Gauravashish.gaurav@uwaterloo.caFormattingIssue #2
* Run yapf, docformatter
* Minor fixesIssue #2
* Run yapf, docformatter
* Minor fixeshttps://git.uwaterloo.ca/wise-lab/wise-move/-/merge_requests/5Bug fix and improve MCTS and others2019-09-09T16:27:03-04:00Jae Young Leejaeyoung.lee@uwaterloo.caBug fix and improve MCTS and others- Fixed error with mean and std
- Improved MCTS.
1. Fixed a bug of starting with start_node;
2. Fixed the miscalculation of mean and std;
3. Added timeout to prevent infinite-loop.
4. Changed output format in mcts.py
...- Fixed error with mean and std
- Improved MCTS.
1. Fixed a bug of starting with start_node;
2. Fixed the miscalculation of mean and std;
3. Added timeout to prevent infinite-loop.
4. Changed output format in mcts.py
5. updated and tested mcts.py
- Refactoring (env -> worlds)
- Change AP ('before_but_close_to_stop_region' --> 'close_to_stop_region')Jae Young Leejaeyoung.lee@uwaterloo.caJae Young Leejaeyoung.lee@uwaterloo.cahttps://git.uwaterloo.ca/wise-lab/wise-move/-/merge_requests/6WiseMove Release (TOMAC-init).2020-04-21T02:15:31-04:00Jae Young Leejaeyoung.lee@uwaterloo.caWiseMove Release (TOMAC-init).A release that contains the code to reproduce the results reported in the initial submission of
Balakrishnan, A., Lee, J., Gaurav, A., Czarnecki, K. and Sedwards, S.,
"Transfer Reinforcement Learning for Autonomous Driving: From W...A release that contains the code to reproduce the results reported in the initial submission of
Balakrishnan, A., Lee, J., Gaurav, A., Czarnecki, K. and Sedwards, S.,
"Transfer Reinforcement Learning for Autonomous Driving: From WiseMove to WiseSim,"
submitted to *the Special Issue of ACM Transactions on Modeling and Computer Simulation (TOMACS)*, 2020.
* Please see [installation.md](https://git.uwaterloo.ca/wise-lab/wise-move/blob/wise-move-tomac-init/documentation/markdown/installation.md) to install the release with 1) all required packages and 2) anaconda virtual environment or docker.
* To reproduce the results, please follow the procedure explained at [repeatability.md](https://git.uwaterloo.ca/wise-lab/wise-move/blob/wise-move-tomac-init/documentation/markdown/repeatability.md) (1. cross_intersection).
* The improved code for the original WiseMove is also provided (click [here](https://git.uwaterloo.ca/wise-lab/wise-move/tree/wise-move-tomac-init/worlds/intersection/simple) or see [repeatability.md](https://git.uwaterloo.ca/wise-lab/wise-move/blob/wise-move-tomac-init/documentation/markdown/repeatability.md) above), but to reproduce the reported numbers in QEST2019, please check out the branch `wise-move-qest-2019` and then follow the instruction in [README.md](https://git.uwaterloo.ca/wise-lab/wise-move/blob/wise-move-qest-2019/README.md) therein.Jae Young Leejaeyoung.lee@uwaterloo.caJae Young Leejaeyoung.lee@uwaterloo.ca