CharlesYang030
244e346b83
- Skill optimization framework with training loop analogy - 11 benchmarks, 4 model backends (Azure OpenAI, Claude, Codex, Qwen) - WebUI for browser-based training control - Pluggable architecture for extending benchmarks and backends
9 lines
378 B
Python
9 lines
378 B
Python
# Vendored from SkillRL (Apache-2.0 License)
|
|
# Original: agent_system/environments/prompts/alfworld.py
|
|
|
|
from skillopt.prompts import load_prompt
|
|
|
|
ALFWORLD_TEMPLATE_NO_HIS = load_prompt("rollout_no_history", env="alfworld")
|
|
ALFWORLD_TEMPLATE = load_prompt("rollout_with_history", env="alfworld")
|
|
ALFWORLD_TEMPLATE_WITH_MEMORY = load_prompt("rollout_with_memory", env="alfworld")
|