Skip to content

Pull requests: xeviknal/aidl-2021-wo-rl

New pull request New
37 Open 35 Closed
37 Open 35 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[Hyper param tuning - early stop / green penalty]
#68 opened Apr 18, 2021 by xeviknal Loading…
3
[Final experiments - REINFORCE] experiment #1 with seed 7081960
#67 opened Apr 18, 2021 by jaimepedretp Loading…
[Final experiments - RL-Baseline] experiment #2 with seed 1000
#66 opened Apr 18, 2021 by jaimepedretp Loading…
Hyperparam tunning - few epochs, high vf coeff (c1) - medium entropy coeff (c2)
#64 opened Apr 18, 2021 by xeviknal Loading…
[PPO - early-step / green penalty] Value Function coeff c1 = 2.0, entropy coeff c2 = 0.08
#63 opened Apr 18, 2021 by xeviknal Loading…
[Final experiments - RL-Baseline] experiment #3 with seed 190421
#58 opened Apr 15, 2021 by ziritrion Loading…
[Final experiments - RL-Baseline] experiment #1 with seed 7081960
#57 opened Apr 15, 2021 by ziritrion Loading…
[PPO experiment] Exp with few epochs, lower gamma
#56 opened Apr 14, 2021 by xeviknal Loading…
PPO - base experiment 1
#55 opened Apr 13, 2021 by xeviknal Loading…
PPO - Add hyperparam tuning with ray.tune
#54 opened Apr 13, 2021 by xeviknal Loading…
4
[Final experiments - REINFORCE] experiment #3 with seed 190421
#53 opened Apr 13, 2021 by ziritrion Loading…
[Final experiments - REINFORCE] experiment #2 with seed 1000
#52 opened Apr 13, 2021 by ziritrion Loading…
PPO-early-stop: finish the episode after 50 steps if avg reward is negative
#51 opened Apr 10, 2021 by xeviknal Loading…
[PPO discrete actions] model v1, experiment 2
#50 opened Apr 8, 2021 by ziritrion Loading…
[PPO discrete actions] model v1, experiment 1
#49 opened Apr 8, 2021 by ziritrion Loading…
[RL-baseline] Model v5, experiment #4
#47 opened Apr 5, 2021 by ziritrion Loading…
[RL-baseline] Model v5, experiment #3
#46 opened Apr 5, 2021 by ziritrion Loading…
reinforce-learningrate #actions1,2,3,4
#45 opened Apr 4, 2021 by jaimepedretp Loading…
[RL-baseline] Model v5, experiment #2
#44 opened Apr 2, 2021 by ziritrion Loading…
[RL-baseline] Model v5, experiment #1
#43 opened Apr 2, 2021 by ziritrion Loading…
1
[RL-baseline] Model v5
#42 opened Apr 2, 2021 by ziritrion Loading…
[RL-baseline] Model v4, experiment #3
#41 opened Mar 31, 2021 by ziritrion Loading…
[RL-baseline] Model v4, experiment #2
#40 opened Mar 31, 2021 by ziritrion Loading…
[RL-baseline] Model v4, experiment #1
#39 opened Mar 30, 2021 by ziritrion Loading…
[RL-baseline] Model v4
#38 opened Mar 30, 2021 by ziritrion Loading…
ProTip! no:milestone will show everything without a milestone.