Hanks1234
/

battleship-ppo-phase3

Reinforcement Learning

stable-baselines3

custom-environment

Model card Files Files and versions

battleship-ppo-phase3

Commit History

Add v11_03 best model (114.08 shots, 50-ep eval, enemy_move_prob=0.02)

3cb41bb
verified

Hanks1234 commited on Mar 24

Update model card

02355ff
verified

Hanks1234 commited on Mar 16

Upload VecNormalize stats

65582b4
verified

Hanks1234 commited on Mar 16

Upload trained Battleship PPO model

e3aff47
verified

Hanks1234 commited on Mar 16

initial commit

c204d6b
verified

Hanks1234 commited on Mar 16