Skip to main content
rLLM home page
Search...
⌘K
Ask AI
rllm-org/rllm
Slack
Slack
Search...
Navigation
Case studies
Experiential Reinforcement Learning
Documentation
Examples
Projects
API Reference
Blog
Case studies
FinQA Financial Agent
DeepScaleR
DeepCoder
DeepSWE
Tongyi DeepResearch
Terminal-Bench-RL
PettingLLMs
SETA
LLM-in-Sandbox
Cogito, Ergo Ludo
Cut the Bill, Keep the Turns
Experiential Reinforcement Learning
V1: Parallel Self-Verification
Case studies
Experiential Reinforcement Learning
Reinforcement learning with an experience-reflection-consolidation loop
Paper
arXiv:2602.13949
Experiential RL introduces a training loop where agents learn through experience, reflect on their performance, and consolidate lessons into improved behavior. Built on rLLM’s training infrastructure.
Was this page helpful?
Yes
No
Cut the Bill, Keep the Turns
Previous
V1: Parallel Self-Verification
Next
⌘I
Assistant
Responses are generated using AI and may contain mistakes.