Feature/grad stats - Githubissues

thiagopbueno / model-aware-policy-optimization

MAPO: Model-Aware Policy Optimization algorithm

GNU General Public License v3.0

1 stars 0 forks source link

Feature/grad stats #94

Closed thiagopbueno closed 5 years ago

thiagopbueno commented 5 years ago

Just added the grad_stats_fn to mapo_policy.py

0xangelo commented 5 years ago

LGTM. The tests that are failing are related to de apply_gradients_fn being changed, which I added an option for in another PR. It is interesting to see that in test_checkpoint the action output is NaN. What might cause this?