Share your thoughts, 1 month free Claude Pro on usSee more

Reinforcement Learning on Craftax Classic

20.5Mean Return

PPO-RNN

Updated 1mo ago

Evaluation Results

Method	Links
PPO-RNN 2026.03		20.5
PPO-RNN 2026.03		20.4
PPO-RNN 2026.03		20.4
PPO-RNN 2026.03		20.3
PPO-RNN 2026.03		19.8
PPO-RNN 2026.03		19.8
PPO-MLP 2026.03		19.5
PPO-MLP 2026.03		19.4
PPO-MLP 2026.03		19.3
PPO-MLP 2026.03		19.3
PPO-MLP 2026.03		19.2
PPO-MLP 2026.03		19.2
PPO-Hybrid 2026.03		19.2
PPO-Hybrid 2026.03		19.2
PPO-Hybrid 2026.03		19
PPO-Hybrid 2026.03		19
PPO-Hybrid 2026.03		18.9
PPO-Hybrid 2026.03		18.4
PPO-Hybrid 2026.03		17.6
PPO-MLP 2026.03		15.3
PPO-RNN 2026.03		14.8
PPO-MLP 2026.03		-0.8
PPO-RNN 2026.03		-0.9
PPO-Hybrid 2026.03		-0.9