# SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling

arXiv: https://arxiv.org/abs/2410.12481 · HTML: https://mlsanity.com/paper/2410.12481/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 15 of 15)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [Pre-Trained Language Models for Interactive Decision-Making](https://mlsanity.com/paper/2202.01771/) (2022)
- [Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning](https://mlsanity.com/paper/2302.02662/) (2023)
- [Guiding Pretraining in Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2302.06692/) (2023)
- [Soft Actor-Critic for Discrete Action Settings](https://mlsanity.com/paper/1910.07207/) (2019)
- [JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models](https://mlsanity.com/paper/2311.05997/) (2023)
- [Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey](https://mlsanity.com/paper/2012.09830/) (2020)
- [Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration](https://mlsanity.com/paper/2002.09253/) (2020)
- [Reinforcing Language Agents via Policy Optimization with Action Decomposition](https://mlsanity.com/paper/2405.15821/) (2024)

## Built on by (most cited first, 5 of 5)

- [MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces](https://mlsanity.com/paper/2502.07709/) (2025)
- [Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents](https://mlsanity.com/paper/2602.00929/) (2026)
- [COVR:Collaborative Optimization of VLMs and RL Agent for Visual-Based Control](https://mlsanity.com/paper/2601.06122/) (2026)
- [Alchemist: Towards the Design of Efficient Online Continual Learning System](https://mlsanity.com/paper/2503.01066/) (2025)
- [Goal-Guided Efficient Exploration via Large Language Model in Reinforcement Learning](https://mlsanity.com/paper/2509.22008/) (2025)

## Abstract (arXiv)

The past years have seen Large Language Models (LLMs) strive not only as generative models but also as agents solving textual sequential decision-making tasks. When facing complex environments where their zero-shot abilities are insufficient, recent work showed online Reinforcement Learning (RL) could be used for the LLM agent to discover and learn efficient strategies interactively. However, most prior work sticks to on-policy algorithms, which greatly reduces the scope of methods such agents could use for both exploration and exploitation, such as experience replay and hindsight relabeling. Yet, such methods may be key for LLM learning agents, and in particular when designing autonomous intrinsically motivated agents sampling and pursuing their own goals (i.e. autotelic agents). This paper presents and studies an adaptation of Soft Actor-Critic and hindsight relabeling to LLM agents. Our method not only paves the path towards autotelic LLM agents that learn online but can also outperform on-policy methods in more classic multi-goal RL environments.