Reinforcement Learning on Craftax Classic
20.5Mean ReturnPPO-RNN
Evaluation results
| Method | Links | |
|---|---|---|
| PPO-RNNArchitecture=RNN, Masking Condition=C4: Masked + KL, Evaluation Protocol=GT2026.03 | 20.5 | |
| PPO-RNNArchitecture=RNN, Masking Condition=C1: Masked, Evaluation Protocol=GT2026.03 | 20.4 | |
| PPO-RNNArchitecture=RNN, Masking Condition=C4: Masked + KL, Evaluation Protocol=Pred2026.03 | 20.4 | |
| PPO-RNNArchitecture=RNN, Masking Condition=C3: Masked + Focal, Evaluation Protocol=GT2026.03 | 20.3 | |
| PPO-RNNArchitecture=RNN, Masking Condition=C2: Unmasked, Evaluation Protocol=GT2026.03 | 19.8 | |
| PPO-RNNArchitecture=RNN, Masking Condition=C2: Unmasked, Evaluation Protocol=Pred2026.03 | 19.8 | |
| PPO-MLPArchitecture=MLP, Masking Condition=C4: Masked + KL, Evaluation Protocol=GT2026.03 | 19.5 | |
| PPO-MLPArchitecture=MLP, Masking Condition=C3: Masked + Focal, Evaluation Protocol=GT2026.03 | 19.4 | |
| PPO-MLPArchitecture=MLP, Masking Condition=C1: Masked, Evaluation Protocol=GT2026.03 | 19.3 | |
| PPO-MLPArchitecture=MLP, Masking Condition=C4: Masked + KL, Evaluation Protocol=Pred2026.03 | 19.3 | |
| PPO-MLPArchitecture=MLP, Masking Condition=C2: Unmasked, Evaluation Protocol=GT2026.03 | 19.2 | |
| PPO-MLPArchitecture=MLP, Masking Condition=C2: Unmasked, Evaluation Protocol=Pred2026.03 | 19.2 | |
| PPO-HybridArchitecture=Hybrid, Masking Condition=C2: Unmasked, Evaluation Protocol=GT2026.03 | 19.2 | |
| PPO-HybridArchitecture=Hybrid, Masking Condition=C2: Unmasked, Evaluation Protocol=Pred2026.03 | 19.2 | |
| PPO-HybridArchitecture=Hybrid, Masking Condition=C3: Masked + Focal, Evaluation Protocol=GT2026.03 | 19 | |
| PPO-HybridArchitecture=Hybrid, Masking Condition=C4: Masked + KL, Evaluation Protocol=GT2026.03 | 19 | |
| PPO-HybridArchitecture=Hybrid, Masking Condition=C1: Masked, Evaluation Protocol=GT2026.03 | 18.9 | |
| PPO-HybridArchitecture=Hybrid, Masking Condition=C4: Masked + KL, Evaluation Protocol=Pred2026.03 | 18.4 | |
| PPO-HybridArchitecture=Hybrid, Masking Condition=C3: Masked + Focal, Evaluation Protocol=Pred2026.03 | 17.6 | |
| PPO-MLPArchitecture=MLP, Masking Condition=C3: Masked + Focal, Evaluation Protocol=Pred2026.03 | 15.3 | |
| PPO-RNNArchitecture=RNN, Masking Condition=C3: Masked + Focal, Evaluation Protocol=Pred2026.03 | 14.8 | |
| PPO-MLPArchitecture=MLP, Masking Condition=C1: Masked, Evaluation Protocol=Pred2026.03 | -0.8 | |
| PPO-RNNArchitecture=RNN, Masking Condition=C1: Masked, Evaluation Protocol=Pred2026.03 | -0.9 | |
| PPO-HybridArchitecture=Hybrid, Masking Condition=C1: Masked, Evaluation Protocol=Pred2026.03 | -0.9 |