Skip to content
Snippets Groups Projects
Select Git revision
  • master default protected
  • qest-2019
2 results
You can move around the graph by using the arrow keys.
Created with Raphaël 2.2.030Apr219Sep15Jul1015Apr26Mar11Feb8654131Jan302924221719Nov181716Update repeatability.mdmastermasterMerge branch 'wise-move-tomac-init' into 'master'Update README.mdqest-2019qest-2019WiseMove Release (TOMAC-init).Merge branch 'bug-fix-and-improve-MCTS-and-others' into 'master'mcts.py updated and tested.Output format change in mcts.py and misc.Change AP ('before_but_close_to_stop_region' --> 'close_to_stop_region')Refactoring (env -> worlds)Improve MCTS.Update README.mdfixed error with mean and stdMerge branch 'gif_readme' into 'master' Update README.mdUpdate README.mdAdded titleincrease heading textAdded only one gifadded highlevel training gifupdated gifschanged width of imagealign gifsUpdated vehicle image, added new gifsadd gifs to readmeMisc updates to docs and scriptsMerge branch 'master' into Train_0.1m_steps_and_improve_WaitMerge branch 'improve_Wait_and_highlevel' into 'master' success check for high level policyMerge branch 'master' into improve_Wait_and_highlevelAdded a high-level policy retrained.Refactoring (change the module name "model_checker" to "verifier")Merge remote-tracking branch 'origin_dev/master'Merge branch 'mcts_rollout_timeout' into 'master' add rollout timeout for MCTSRefactoring (change the module name "model_checker" to "verifier")Wait (and the others slightly) improved.MCTS FixesMerge branch 'retraining_wait_maneuver' into 'master' Successful high-level policy (6-hidden layers, 1m training).High-level policy trained for 1m steps with 3-hidden layers.