mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-28 06:51:16 +08:00
initial RL training tools and loop
This commit is contained in:
12
toolsets.py
12
toolsets.py
@@ -90,6 +90,18 @@ TOOLSETS = {
|
||||
"includes": []
|
||||
},
|
||||
|
||||
"rl": {
|
||||
"description": "RL training tools for running reinforcement learning on Tinker-Atropos",
|
||||
"tools": [
|
||||
"rl_list_environments", "rl_select_environment",
|
||||
"rl_get_current_config", "rl_edit_config",
|
||||
"rl_start_training", "rl_check_status",
|
||||
"rl_stop_training", "rl_get_results",
|
||||
"rl_test_inference", "rl_list_runs"
|
||||
],
|
||||
"includes": []
|
||||
},
|
||||
|
||||
# Scenario-specific toolsets
|
||||
|
||||
"debugging": {
|
||||
|
||||
Reference in New Issue
Block a user