JibrilExe
20ba63a303
fix: ruff format
2026-04-14 21:14:26 +02:00
JibrilExe
0a9bf2e0a5
fix: dont store clipped action, and upgraded reward scale
2026-04-14 20:30:21 +02:00
JibrilExe
7a87facc8a
feat: value loss clipping
2026-04-14 19:23:20 +02:00
JibrilExe
1f8fdbdc59
feat: observation normalization
2026-04-14 19:07:15 +02:00
JibrilExe
631d01ebf6
feat: log distance to target for each env
2026-04-12 13:09:53 +02:00
JibrilExe
c5a8dd2b3a
feat: expanded used var doc, and added distance to target log
2026-04-12 12:54:48 +02:00
JibrilExe
1c328bdde1
fix: observation filtering, action clipping, log_std clip, reward discount, bigger MLP
2026-04-12 11:12:46 +02:00
JibrilExe
c0e7569773
feat: More low lvl logs, reward, advantage, returns
2026-04-11 13:42:52 +02:00
JibrilExe
aad086cb7d
fix: Merge with origin/dev
2026-04-10 15:20:22 +02:00
JibrilExe
1ef257544a
feat: first approach to action clipping
2026-04-10 15:18:33 +02:00
JibrilExe
b7e2beb65d
fx(cleanup): removed meaningless comments, added typing and renamed lossinfo to trainingmeasurements
2026-04-10 08:31:52 +02:00
JibrilExe
6e942d896b
fix(gae): fixes #31
2026-04-10 08:23:34 +02:00
cedric
bf6434ea6c
fix(cleanup): ruff format
2026-04-09 22:13:07 +00:00
vsc46589 vscuser
71349af5b9
feat(logging): added avg episode at which terminated or truncated happened
2026-04-10 00:11:18 +02:00
vsc46589 vscuser
f7428f9d90
feat(logging): added amount of envs that truncated and terminated
2026-04-09 23:40:58 +02:00
vsc46589 vscuser
b839024e6e
feat(logging): added explained variance chart
2026-04-09 23:14:52 +02:00
849581fcfd
fix: linting
2026-04-09 00:37:02 +02:00
2f31df412b
fix(log): avoid duplicates in logs
2026-04-09 00:14:28 +02:00
75c6d5bacd
fix: mypy complaints
2026-04-09 00:02:18 +02:00
f6dc9c8e7f
feat: add build system, mypy and editable source
2026-04-09 00:02:13 +02:00
cd7169a75f
docs(log): extend how to use UnifiedLogger
2026-04-08 20:47:48 +02:00
e9b52e9e8f
refactor: migrate configs from JSON to YAML
2026-04-08 20:37:47 +02:00
ae483b306f
feat(log): add SimpleLogger for terminal logging without external backends
2026-04-08 20:26:26 +02:00
46ae13abc3
feat(log): non-interactive logging, incl. progress bar
2026-04-08 19:54:05 +02:00
faf31567e8
refactor(log): PPOTrainer
2026-04-08 19:32:48 +02:00
795ae48520
feat(log): add TensorBoard support and enhance WandB API key checking
2026-04-08 18:58:33 +02:00
d4ac45b34e
feat(logger): updated run_name format and added runtime log level filtering
2026-04-08 18:53:31 +02:00
512272d6ab
Merge branch 'dev' into feat/wandb-logging
2026-04-08 16:15:38 +02:00
Robin Meersman
431ecdf4b4
restructure
2026-04-06 17:02:40 +02:00
Robin Meersman
8a2f8b14bc
fix(PPOTrainer.py, PPOArgs.py): added hyperparam config path to cli args, fixed missing arguments error in _step call
2026-04-06 14:07:46 +02:00
Robin Meersman
84f6fbd76e
fix: merge conflict
2026-04-06 12:03:12 +02:00
fb346a06b2
refactor(hpc): ruff checks
2026-04-05 08:06:26 +02:00
ef380d073f
Merge branch 'dev' into ci/hpc
2026-04-05 08:01:38 +02:00
24ae7a2399
fix(hpc): overriding args
2026-04-05 07:35:01 +02:00
d33dc32506
feat(hpc): debug logging
2026-04-05 07:17:48 +02:00
ed20325fef
feat(hpc): rename config_path to env_config_path and support YAML configs
2026-04-04 19:07:01 +02:00
0aeff0f2da
feat(hpc): include git hash in run_name for traceability
2026-04-04 19:02:06 +02:00
92db8c2591
feat(hpc): support run_dir staging and update docs
...
- Add run_dir and checkpoint_frequency to PPOArgs
- Update train.py to use run_dir for SummaryBoard, model saving, and loss plots
- Create configs/production_training.yaml for HPC production runs
- Update HPC.md with run_dir staging strategy details
2026-04-04 18:59:05 +02:00
Robin Meersman
62e11ce243
fix(PPOTrainer.py): bug fixes regarding jax.jit
2026-04-03 15:22:51 +02:00
Robin Meersman
1cb0e2d95b
fix(merge): fixed merge conflict
2026-04-03 12:58:40 +02:00
cedric
3104678f96
fix: uniform naming
2026-04-03 08:11:50 +00:00
cedric
1c4e40b5fb
fix: uniform naming of models accross code
2026-04-02 18:37:37 +00:00
cedric
79221372df
fix: uniform generic network naming
2026-04-02 18:18:10 +00:00
cedric
40c7e32344
feat: more generic naming for critic, since messager will use the same
2026-04-02 18:11:49 +00:00
cedric
729f122be4
fix: removed useless comment
2026-04-02 18:00:53 +00:00
cedric
95840b789b
fix: usage of field because flax wont allow mutable class object
2026-04-02 17:59:48 +00:00
cedric
9879fea9e2
fix: refactored rl folder into mlps
2026-04-02 17:50:44 +00:00
cedric
15ae86796f
feat: generic network
2026-04-02 17:38:46 +00:00
2263c97fe8
style: ruff format
2026-04-02 17:36:41 +00:00
cmekeirl
4e3eee8ac6
Basic centralized model
2026-04-02 17:36:41 +00:00
