What matters in reinforcement learning for tractography - Trained models
Bibliographic record
Abstract
Trained models for "What matters in reinforcement learning for tractography". These can be loaded to track on arbitrary data. Nomenclature goes as follows: [RL algorithm]_Train[Dataset][Extra]Exp[1-5] RL algorithm can be one of the following: VPG, A2C, ACKTR, TRPO, PPO, DDPG, TD3, SAC, SAC_Auto Dataset refers to the dataset used for training, can be either FiberCup or ISMRM2015 Exp1 to Exp2 refer to the experiment the agent were trained for Extra refers to sub-experiments in the case of experiments 3-5. Each folder contains another subfolder named as the ID of the training batch. Usually the date and time the training was started. The subfolder contains folders 1111, 2222, 3333, 4444, 5555. These are the random seeds used to initialise the 5 training runs per agent. Each of these subfolders then contain a "model" subfolder, which contains the pytorch weights (.pth) and hyperparameters (hyperparameters.json) of the trained agents. For example: SAC_Auto_FiberCupNoWMTrainExp4: -- 2023-03-22-07_38_30: --1111 --2222 --3333 --4444 --5555: --model: --last_model_state_actor.pth --last_model_state_critic.pth --hyperparameters.json Refer to https://github.com/scil-vital/TrackToLearn for usage.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.038 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.005 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.013 | 0.004 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".