Shams1363
/

ppo-SnowballTarget

Reinforcement Learning

deep-reinforcement-learning

ML-Agents-SnowballTarget

Eval Results (legacy)

Model card Files Files and versions

Metrics Training metrics Community

ppo-SnowballTarget / config.json

Commit History

Trained SnowballTarget with tuned PPO params - Mean Reward 26.8

f194818
verified

Shams1363 commited on 28 days ago