NREL/rlmolecule
A reinforcement learning library for material and molecule optimization
PythonBSD-3-Clause
Issues
- 1
- 0
tf 2.7.0 issues
#101 opened by pstjohn - 1
Documentation
#107 opened by rohanvarm - 1
postgresQL modularization
#20 opened by pstjohn - 2
- 0
need unittests for rlmolecule.gym
#83 opened by pstjohn - 1
performance monitoring
#27 opened by pstjohn - 0
- 0
Allow users not to cache policy inputs
#75 opened by pstjohn - 0
preprocessor.json doesn't have extra atom types needed for expanded QED optimization
#77 opened by pstjohn - 0
Rethink how we do masking
#74 opened by pstjohn - 0
database structuring
#41 opened by pstjohn - 0
check synthesizability
#43 opened by pstjohn - 1
add setup.py to rlmolecule
#57 opened by pstjohn - 1
Users can accidently provide an enviornment where duplicate actions get returned
#68 opened by pstjohn - 1
policy_digest not sufficient to distringuish possible children in store_search_statistics
#69 opened by pstjohn - 1
Can't kekulize mol
#61 opened by jlaw9 - 1
- 0
investigate alternative molecular generation methods, compare AZ to existing methods w/ GuacaMol
#26 opened by pstjohn - 2
TF serving
#16 opened by pstjohn - 1
Continuous model training
#10 opened by pstjohn - 0
Heterogeneous job support?
#22 opened by pstjohn - 0
some inference and monitoring tools
#23 opened by pstjohn - 0
ranked reward alernatives?
#24 opened by pstjohn - 0
game class
#9 opened by pstjohn - 0
- 2
PostgresQL configuration
#13 opened by pstjohn - 0
better config handing
#8 opened by pstjohn - 0
Better handling of ranked rewards
#5 opened by davebiagioni - 0
Better handling of out-of-scope molecules
#19 opened by pstjohn - 0
separate `ranked_reward` and `true_reward`
#18 opened by pstjohn - 0
New radical stability reward
#15 opened by pstjohn