Spaces:

ianalin123
/

origami_env

Running

App Files Files Community

origami_env / training

80 kB

4 contributors

History: 28 commits

ianalin123's picture

feat(v3): hybrid GRPO + SFT training with expert beam search

4d27d34 3 days ago

Dockerfile.train

855 Bytes

feat: Railway deployment + multi-task GRPO + Modal B200 training 3 days ago
__init__.py

0 Bytes

Origami RL environment with Three.js viewer 4 days ago
curriculum.py

574 Bytes

fix(v3): include multi-step tasks from curriculum start 3 days ago
env_pool.py

1.09 kB

feat(v3): implement core building blocks for multi-step RL training 3 days ago
expert_search.py

5.43 kB

feat(v3): hybrid GRPO + SFT training with expert beam search 3 days ago
gigpo.py

3.76 kB

feat(v3): implement core building blocks for multi-step RL training 3 days ago
prompt_builder.py

3.26 kB

fix(v3): prompt perturbation to break deterministic outputs 3 days ago
reward.py

9.33 kB

feat(v2): add extract_crease_json and valid_crease reward to training/reward.py 3 days ago
rollout.py

3.62 kB

fix(v3): guarantee reward variance with num_per_task and higher temp 3 days ago
train_grpo.py

12.4 kB

feat(v2): update train_grpo.py for step-level prompts and per_step_reward 3 days ago
train_origami.ipynb

19.8 kB

revert: restore train_origami.ipynb to Prasanna's exact version 3 days ago
train_v3.py

19.3 kB

feat(v3): hybrid GRPO + SFT training with expert beam search 3 days ago
trajectory.py

596 Bytes

feat(v3): implement core building blocks for multi-step RL training 3 days ago