a033e77697
intorducing jax for computation
2026-01-22 21:02:10 +01:00
40e0b201e6
chore: init code for jax core
2026-01-22 13:10:15 +01:00
a217d53556
feat: translating features to jax
2026-01-22 13:10:01 +01:00
a6e6cc5d60
feat: baseline setup for RL modeling
2026-01-22 12:52:41 +01:00
fa89347c4e
feat: expanding market observation space
2026-01-22 11:48:24 +01:00
2b3d937be6
feat: fixing alignment w premiums and specific extraction of data
2026-01-22 11:46:32 +01:00
20c47fe85f
review: planning environment refactoring
2026-01-22 11:40:47 +01:00
b7161573d7
chore: mini docs
2026-01-22 11:40:27 +01:00
c15bb1882e
chore: training and data refactors
2026-01-22 11:40:12 +01:00
dee6f573e3
feat: contaminator and training
2026-01-21 19:12:56 +01:00
2ed200f870
chore: make lib backwards compatible
2026-01-21 19:12:35 +01:00
56308ecb10
chore: export repeated methods into lib
2026-01-21 19:12:11 +01:00
7fcd18c3cb
chore: remove boilerplate
2026-01-21 19:11:54 +01:00
5f607a58eb
acapting some architectures
2026-01-21 18:22:39 +01:00
6aad196234
migrating weak learning
2026-01-21 18:22:31 +01:00
e5060babfa
feat: initial feature engineering of trajectories
2026-01-21 14:05:39 +01:00
80863e9b17
strong dataset gathering
2026-01-21 14:05:30 +01:00
a5029f2eab
feat: weak train scaffold
2026-01-21 11:27:03 +01:00
c102ac482e
chore: extra commenting
2026-01-21 11:11:49 +01:00
08ade8dc89
feat: wip contaminator
2026-01-20 21:00:47 +01:00
95d4f0cee2
chore: ignores
2026-01-13 19:50:36 +01:00
3072e5f46e
refactor models computations
2026-01-13 16:51:00 +01:00
a1e3166322
chore: refactor the loader class
2026-01-13 16:46:17 +01:00
6f361b96a8
feat: joint loader
2026-01-13 16:42:50 +01:00
eea019ab3f
feat: introduction of agentinc MDPs and KL divergence of > 2
2026-01-13 15:57:05 +01:00
a36973cb42
feat: forgot airflow helper staging
2026-01-13 15:37:06 +01:00
96180e9af1
feat: added a runner script for agent orchestration
2026-01-13 15:36:20 +01:00
Daniel Alves Rösel
e60c0c64e1
Pre run web refactors ( #43 )
...
* chore: refactor date utilities
* feat: improve images of hotel rooms
* fix: adding date utils
2026-01-13 15:35:27 +01:00
90f57cb9b9
chore: styling and title updates
2026-01-13 15:09:52 +01:00
d865357695
chore: fixing visual bugs in cart
2026-01-13 15:05:33 +01:00
961302a21a
chore: better test consistency before agnet
2026-01-12 22:33:47 +01:00
0d214a469f
planning
2026-01-12 20:59:09 +01:00
acf731efcb
feat: integration of pipeline hooks into testing
2026-01-12 13:37:48 +01:00
9a8525a854
chore: refactor to better map end to end
2026-01-12 11:02:48 +01:00
29f51d56d1
pdf rendering
2026-01-12 11:02:48 +01:00
c56c7f6537
featuer: dot exporter
2026-01-12 11:02:48 +01:00
b1882b6049
feature: MDP behavior mappers (unlinked)
2026-01-12 11:02:48 +01:00
57a7e0c571
simple code cleanup
2026-01-12 11:02:48 +01:00
c8c44d0453
refactor to align moer with research in the env sims
2026-01-12 11:02:48 +01:00
f950565264
tailored docker compose image for secondary tenaordboard
2026-01-12 11:02:48 +01:00
aae124f5ea
improved implementation
2026-01-12 11:02:48 +01:00
c5caee21b1
formlating the reward simply
2026-01-12 11:02:48 +01:00
fe7dafed0a
high level defintion
2026-01-12 11:02:48 +01:00
fa65fe992d
initial environemnt definitions
2026-01-12 11:02:48 +01:00
Daniel Alves Rösel
221e71a503
E2e testing of pricing ( #42 )
...
* a simp0le scaffold
* feature: simple npm setup
* feature: testing setup and dummy scenarios
* chore: dumping kafak just via backend
* chore: dcleaning gitignore
* features: boilerplate fixtures and stuff
* test: extra tests
* chore: update the test suite to be callable via makefile
* chore: cleaning
* chore: updating interactions setup
* small cleaning
* chore: cleaning shitty code
2026-01-12 11:02:18 +01:00
Daniel Alves Rösel
f2271e368e
34 initial discriminator of interaction data ( #38 )
...
* feat: training pipeline + tensorboard
* tesnorboard forgot
* chore: ml basic boilerplate
* feat: naive architecture as start
* eval setup
* chore: parquet exporting of data
* chore: updating requirements necesary
* feat: separating modules and adding training logs paths
* Update experiments/ml/train.py
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* fix: new path for runs
* fix: undoing ai slop code
* chore: modules and reqs
---------
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-14 18:58:42 +01:00
Daniel Alves Rösel
a1916c966c
32 refine data pipeline training data construction ( #37 )
...
* feature: modularized feature engineering for ml setup (new pipeline)
* chore: updating imports properly
* test: updating fixtures with ua and meta
* chore: migrating code ignore groups
* chore: syntax cleaning and code quality
* chore: fixing pipeline data compatability
* Update experiments/procesing/steps/session.py
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* chore: refactoring and dixing path joining
* chore: refactoring function definition to avoid reinit
---------
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-12 12:15:15 +01:00
Daniel Alves Rösel
a2a443c027
Update README with project badges and links
...
Added badges for build status, TPU support, and Vercel deployments.
2025-12-12 10:21:11 +01:00
Daniel Alves Rösel
ef98141ca8
Catchup airline ( #31 )
...
* chore: update provider and pricing snitch with agnostic system
* cloning pipelines per mode instance
* updating airline hero section
* fix: must keep airflow secretkey
* fix: fixture update to hotel not shop
* chore: refactored to factory design pattern of pipelines
* chore: clean up definition of composite class of providers
2025-12-11 21:56:12 +01:00
d45b344264
fixing public routing for store modes
2025-12-08 15:00:37 +01:00
