Experiential Reinforcement Learning

Abstract

Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is challenging, as LMs must implicitly infer how observed failures should translate into behavioral changes for future iterations. We introduce Experiential Reinforcement Learning (ERL), a training paradigm that embeds an explicit experience-reflection-consolidation loop into the reinforcement learning process. Given a task, the model generates an initial attempt, receives environmental feedback, and produces a reflection that guides a refined second attempt, whose success is reinforced and internalized into the base policy. This process converts feedback into structured behavioral revision, improving exploration and stabilizing optimization while preserving gains at deployment without additional inference cost. Across sparse-reward control environments and agent

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score2.58
• arxiv keyshi2026experiential

Related papers

• Experiential Explanations For Reinforcement Learning (2022)2.26
• Ecological Reinforcement Learning (2020)8.35
• From Laws To Motivation: Guiding Exploration Through Law-based Reasoning And Rewards (2024)0.00
• Mental Modeling Of Reinforcement Learning Agents By Language Models (2024)0.00
• Aligning Humans And Robots Via Reinforcement Learning From Implicit Human Feedback (2025)2.26
• LERO: Llm-driven Evolutionary Framework With Hybrid Rewards And Enhanced Observation For Multi-agent Reinforcement Learning (2025)3.58
• Learn The Ropes, Then Trust The Wins: Self-imitation With Progressive Exploration For Agentic Reinforcement Learning (2025)0.00
• A Survey On Enhancing Reinforcement Learning In Complex Environments: Insights From Human And LLM Feedback (2024)0.00