Commit Graph

163 Commits

Author SHA1 Message Date
Daniel Alves Rösel
9843c5deab Merge pull request #51 from velocitatem/feat-strong-learning-implementation-with-data-contamination
Feat strong learning implementation with data contamination
2026-01-31 10:15:09 +01:00
13959e4b28 chore: bug fixes 2026-01-31 10:13:07 +01:00
Daniel Alves Rösel
2f481bd94b Merge branch 'agent-behavior-loader-developemen' into feat-strong-learning-implementation-with-data-contamination 2026-01-31 10:08:59 +01:00
72877439ca feat: contaminator and training 2026-01-31 09:48:20 +01:00
0f5f8affab chore: make lib backwards compatible 2026-01-31 09:48:20 +01:00
ee70f02a1f chore: export repeated methods into lib 2026-01-31 09:48:20 +01:00
22a2c255bd chore: remove boilerplate 2026-01-31 09:48:20 +01:00
ccc19f3493 acapting some architectures 2026-01-31 09:48:20 +01:00
00e3eff2fa migrating weak learning 2026-01-31 09:48:20 +01:00
440371dba4 feat: initial feature engineering of trajectories 2026-01-31 09:48:20 +01:00
b05b510f70 strong dataset gathering 2026-01-31 09:48:20 +01:00
04907df393 feat: weak train scaffold 2026-01-31 09:48:20 +01:00
b2f0746c01 chore: extra commenting 2026-01-31 09:48:20 +01:00
7b2d80ac4c feat: wip contaminator 2026-01-31 09:48:20 +01:00
0ce12fbc3b chore: ignores 2026-01-31 09:48:17 +01:00
e9cf5f0736 refactor models computations 2026-01-31 09:46:44 +01:00
82b54428b7 chore: refactor the loader class 2026-01-31 09:46:44 +01:00
87a35fad2c feat: joint loader 2026-01-31 09:46:44 +01:00
af23d2f736 feat: introduction of agentinc MDPs and KL divergence of > 2 2026-01-31 09:46:44 +01:00
9cb2b0fc44 feat: forgot airflow helper staging 2026-01-31 09:46:44 +01:00
7c330a19c6 feat: added a runner script for agent orchestration 2026-01-31 09:46:44 +01:00
Daniel Alves Rösel
eb95060380 Pre run web refactors (#43)
* chore: refactor date utilities

* feat: improve images of hotel rooms

* fix: adding date utils
2026-01-31 09:46:44 +01:00
61dd621532 chore: styling and title updates 2026-01-31 09:46:44 +01:00
4c368d48f2 chore: fixing visual bugs in cart 2026-01-31 09:46:44 +01:00
3c141a4b6c chore: better test consistency before agnet 2026-01-31 09:46:44 +01:00
e89cb263d4 planning 2026-01-31 09:46:44 +01:00
62a4008c29 feat: integration of pipeline hooks into testing 2026-01-31 09:46:44 +01:00
8b429b7a8e chore: refactor to better map end to end 2026-01-31 09:46:44 +01:00
f9bf3de71e pdf rendering 2026-01-31 09:46:44 +01:00
131323ef56 featuer: dot exporter 2026-01-31 09:46:44 +01:00
ec4cf074e6 feature: MDP behavior mappers (unlinked) 2026-01-31 09:46:44 +01:00
6a06a8af4a simple code cleanup 2026-01-31 09:46:44 +01:00
3fa98f375d refactor to align moer with research in the env sims 2026-01-31 09:46:44 +01:00
201c98bcac improved implementation 2026-01-31 09:46:44 +01:00
8a08458478 formlating the reward simply 2026-01-31 09:46:44 +01:00
7d09232e48 high level defintion 2026-01-31 09:46:44 +01:00
20132c084c initial environemnt definitions 2026-01-31 09:46:41 +01:00
26abff5864 chore: fixing tests with seed determinism 2026-01-30 13:57:40 +01:00
4c7d9362af chore: envs for e2e 2026-01-30 13:55:22 +01:00
ea45801845 chore: removing the lab byproduct 2026-01-30 13:22:22 +01:00
Daniel Alves Rösel
574e05d9e0 Merge pull request #50 from velocitatem/new-simulation-environment-development
New simulation environment development
2026-01-30 13:19:53 +01:00
52fe865598 feature: drafting studies directory 2026-01-30 13:18:20 +01:00
28d3f6853e chore: refactor wrapper 2026-01-30 13:17:12 +01:00
10e8397eec chore: bette rplotting 2026-01-29 13:11:52 +01:00
772772b5b9 chore: better wrapping amd more performant 2026-01-29 10:01:53 +01:00
6e06081d60 porting to better 2026-01-28 16:09:28 +01:00
83d9bb2552 chore: properly developing 2026-01-28 14:04:57 +01:00
fa2aca8b13 chore: rough migration of environment configuration 2026-01-26 14:12:41 +01:00
cd6c3d6006 chore: migrating thesis case definition 2026-01-26 13:19:55 +01:00
98a9a3738c fix: coi better defined and aligned and sac improved 2026-01-25 10:36:37 +01:00