keiohta / tf2rl / 318

Builds Branch Commit Type Ran Committer Via Coverage
318 master Merge branch 'continuous_training' push keiohta travis-ci pending completion   set done
317 continuous_training Periodically serach the latest model file and load it to evaluate continuously push keiohta travis-ci pending completion   set done
316 0.1.11 Upgrade to 0.1.11 push keiohta travis-ci pending completion   set done
315 master Upgrade to 0.1.11 push keiohta travis-ci pending completion   set done
314 master Merge branch 'issue_79' push keiohta travis-ci pending completion   set done
313 remove_roboschool Fix typo push keiohta travis-ci pending completion   set done
303 0.1.10 Evaluate policy and save model while collecting transitions in on_policy_trainer push keiohta travis-ci pending completion   set done
302 master Evaluate policy and save model while collecting transitions in on_policy_trainer push keiohta travis-ci pending completion   set done
301 master Fix a bug of duplicately saving stored data push keiohta travis-ci pending completion   set done
299 mujoco Add PPO script push keiohta travis-ci pending completion   set done
298 master Fix a bug of inputting removed argument in SAC push keiohta travis-ci pending completion   set done
297 ppo Fix a bug of inputting removed argument in SAC push keiohta travis-ci pending completion   set done
291 ppo Fix a bug of sampling experience in on policy trainer #76 push keiohta travis-ci pending completion   set done
290 ppo Modify hyper-parameters of PPO MuJoCo experiments to fit them to Deep Learning that Matters push keiohta travis-ci pending completion   set done
289 master Merge pull request #73 from estshorter/fix-doc Fix a spelling error in README.md push web-flow travis-ci pending completion   set done