Tibo De Peuter
92db8c2591
- 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
24 lines
503 B
YAML
24 lines
503 B
YAML
# Full PPO training config for Brittle Star (HPC Production)
|
|
exp_name: "production_training"
|
|
seed: 1
|
|
track: true
|
|
capture_video: true
|
|
save_model: true
|
|
checkpoint_frequency: 100 # not yet implemented in train.py but here for future use
|
|
|
|
# Scaling for HPC (using A100 GPU slices)
|
|
num_envs: 128
|
|
total_timesteps: 10000000
|
|
num_steps: 128
|
|
num_minibatches: 4
|
|
update_epochs: 4
|
|
|
|
# Algorithm
|
|
learning_rate: 2.5e-4
|
|
anneal_lr: true
|
|
gamma: 0.99
|
|
gae_lambda: 0.95
|
|
clip_coef: 0.1
|
|
ent_coef: 0.01
|
|
vf_coef: 0.5
|
|
cuda: true
|