TLA with Hierarchical Reward Functions

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Playing Games3 results

OpenAI GymonPendulum-v1
Action Repetition· 2024-11-23
0.8073
SOTA
Creating Hierarchical Dispositions of Needs in an Agent arXiv:2412.00044
OpenAI GymonPendulum-v1
Mean Reward· 2024-11-23
-125.02
SOTA
Creating Hierarchical Dispositions of Needs in an Agent arXiv:2412.00044
OpenAI GymonPendulum-v1
Average Decisions· 2024-11-23
38.6
best: 62.31 (TLA)
Creating Hierarchical Dispositions of Needs in an Agent arXiv:2412.00044