Improved robust model (median 13.5, mean 17.25 over 200 eps); standard arch h=64 aa88721 verified sourav6565 commited on Jun 30
Fix architecture to standard course Policy (uniform h_size=64); mean_reward 12.36 a5d2957 verified sourav6565 commited on Jun 30
Add certified Reinforce Pixelcopter-PLE-v0 agent (mean_reward 19.08) fa7b2e0 verified sourav6565 commited on Jun 30