Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning

• URL: http://arxiv.org/abs/2406.04815v3
• Date: Wed, 06 Nov 2024 13:24:41 GMT
• Title: Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning
• Abstract summary: We introduce Skill-aware Mutual Information (SaMI), an optimisation objective that aids in distinguishing context embeddings according to skills. We then propose Skill-aware Noise Contrastive Estimation (SaNCE), a $K$-sample estimator used to optimise the SaMI objective. We empirically find that RL agents that learn by maximising SaMI achieve substantially improved zero-shot generalisation to unseen tasks.
• Score: 14.62474759939562
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Meta-Reinforcement Learning (Meta-RL) agents can struggle to operate across tasks with varying environmental features that require different optimal skills (i.e., different modes of behaviour). Using context encoders based on contrastive learning to enhance the generalisability of Meta-RL agents is now widely studied but faces challenges such as the requirement for a large sample size, also referred to as the $\log$-$K$ curse. To improve RL generalisation to different tasks, we first introduce Skill-aware Mutual Information (SaMI), an optimisation objective that aids in distinguishing context embeddings according to skills, thereby equipping RL agents with the ability to identify and execute different skills across tasks. We then propose Skill-aware Noise Contrastive Estimation (SaNCE), a $K$-sample estimator used to optimise the SaMI objective. We provide a framework for equipping an RL agent with SaNCE in practice and conduct experimental validation on modified MuJoCo and Panda-gym benchmarks. We empirically find that RL agents that learn by maximising SaMI achieve substantially improved zero-shot generalisation to unseen tasks. Additionally, the context encoder trained with SaNCE demonstrates greater robustness to a reduction in the number of available samples, thus possessing the potential to overcome the $\log$-$K$ curse.

Related papers

• Learning Generalizable Behaviors for Terminal Agents [72.62493560701414]
  We propose a simple training recipe that improves reward quality by filtering low-quality environments and augmenting outcome rewards with process-level behavior regularization.<n>Using this recipe, our RL-trained agent account the best performance among evaluated open-source RL-trained 8B models across four terminal-agent benchmarks.
  arXiv  Detail & Related papers  (2026-08-23T22:34:40Z)
• Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents [11.967142343676171]
  We propose BCSD (Bi Context Self-Distillation), a framework that combines self-distillation and reinforcement learning to train agents to use external skills more effectively.<n> Experiments on ALFWorld and WebShop demonstrate that BCSD achieves the strongest overall performance across model scales.
  arXiv  Detail & Related papers  (2026-08-10T12:53:06Z)
• UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs [28.526758776988256]
  We introduce UpSkill, a training time method that adapts Mutual Information Skill Learning to large language models.<n>We show that UpSkill improves multi-attempt metrics on the stronger base models.<n>We find both empirical and theoretical evidence that improvements in pass@k are closely tied to the mutual information objective.
  arXiv  Detail & Related papers  (2026-02-25T15:34:14Z)
• Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning [39.84288631342219]
  We analyze large-scale reinforcement learning training runs from the sophisticated environment of Full-Press Diplomacy.<n>We introduce Meta-Autointerp, a method for grouping SAE features into interpretable hypotheses about training dynamics.<n>We find that even subjectively interesting and seemingly helpful SAE features may be worse than useless to humans.
  arXiv  Detail & Related papers  (2026-02-05T01:21:22Z)
• Multimodal Reinforcement Learning with Agentic Verifier for AI Agents [131.46008226323423]
  Argos is a principled multimodal reward agent to train reasoning models for agentic tasks.<n>By leveraging our agentic verifier across both SFT data and RL training, our model achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2025-12-03T04:42:47Z)
• Demystifying Reinforcement Learning in Agentic Reasoning [90.3737088727791]
  We conduct a comprehensive and systematic investigation to demystify reinforcement learning in agentic reasoning.<n>We highlight our key insights: (i) replacing stitched synthetic trajectories with real end-to-end tool-use trajectories yields a far stronger SFT.<n> Exploration-friendly techniques are crucial for agentic RL, such as clip higher, overlong reward shaping, and maintaining adequate policy entropy could improve the training efficiency.
  arXiv  Detail & Related papers  (2025-10-13T17:57:15Z)
• Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One [28.264011412168347]
  Model ensemble is a useful approach in reinforcement learning (RL) for training effective agents.<n>We propose LLM-Ens, a novel approach that enhances RL model ensemble with task-specific semantic understandings.
  arXiv  Detail & Related papers  (2025-05-21T09:35:43Z)
• ToolRL: Reward is All Tool Learning Needs [54.16305891389931]
  Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities. Recent advancements in reinforcement learning (RL) have demonstrated promising reasoning and generalization abilities. We present the first comprehensive study on reward design for tool selection and application tasks within the RL paradigm.
  arXiv  Detail & Related papers  (2025-04-16T21:45:32Z)
• SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks [110.20297293596005]
  Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks. Existing multi-turn RL algorithms for optimizing LLM agents fail to perform effective credit assignment over multiple turns while leveraging the generalization capabilities of LLMs. We propose a novel RL algorithm, SWEET-RL, that uses a carefully designed optimization objective to train a critic model with access to additional training-time information. Our experiments demonstrate that SWEET-RL achieves a 6% absolute improvement in success and win rates on ColBench compared to other state-of-the-art multi-turn RL algorithms.
  arXiv  Detail & Related papers  (2025-03-19T17:55:08Z)
• Learning to Optimize for Reinforcement Learning [58.01132862590378]
  Reinforcement learning (RL) is essentially different from supervised learning, and in practice, these learneds do not work well even in simple RL tasks. Agent-gradient distribution is non-independent and identically distributed, leading to inefficient meta-training. We show that, although only trained in toy tasks, our learned can generalize unseen complex tasks in Brax.
  arXiv  Detail & Related papers  (2023-02-03T00:11:02Z)
• Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation [17.165083095799712]
  We study the problem of few-shot adaptation in the context of human-in-the-loop reinforcement learning. We develop a meta-RL algorithm that enables fast policy adaptation with preference-based feedback.
  arXiv  Detail & Related papers  (2022-11-20T03:55:09Z)
• Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery [12.586875201983778]
  Deep Reinforcement Learning (RL) has emerged as a powerful paradigm for training neural policies to solve complex control tasks. We show that Quality Diversity (QD) methods are a competitive alternative to information-theory-augmented RL for skill discovery.
  arXiv  Detail & Related papers  (2022-10-06T11:06:39Z)
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
  Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment. We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent. We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
  arXiv  Detail & Related papers  (2022-09-24T14:22:29Z)
• Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks [56.63855534940827]
  This work introduces a novel objective function to learn an action translator among training tasks. We theoretically verify that the value of the transferred policy with the action translator can be close to the value of the source policy. We propose to combine the action translator with context-based meta-RL algorithms for better data collection and more efficient exploration during meta-training.
  arXiv  Detail & Related papers  (2022-07-19T04:58:06Z)
• REIN-2: Giving Birth to Prepared Reinforcement Learning Agents Using Reinforcement Learning Agents [0.0]
  In this paper, we introduce a meta-learning scheme that shifts the objective of learning to solve a task into the objective of learning to learn to solve a task (or a set of tasks) Our model, named REIN-2, is a meta-learning scheme formulated within the RL framework, the goal of which is to develop a meta-RL agent that learns how to produce other RL agents. Compared to traditional state-of-the-art Deep RL algorithms, experimental results show remarkable performance of our model in popular OpenAI Gym environments.
  arXiv  Detail & Related papers  (2021-10-11T10:13:49Z)
• Meta-Reinforcement Learning in Broad and Non-Parametric Environments [8.091658684517103]
  We introduce TIGR, a Task-Inference-based meta-RL algorithm for tasks in non-parametric environments. We decouple the policy training from the task-inference learning and efficiently train the inference mechanism on the basis of an unsupervised reconstruction objective. We provide a benchmark with qualitatively distinct tasks based on the half-cheetah environment and demonstrate the superior performance of TIGR compared to state-of-the-art meta-RL approaches.
  arXiv  Detail & Related papers  (2021-08-08T19:32:44Z)
• Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning [114.07623388322048]
  We discuss how the standard goal-conditioned RL (GCRL) is encapsulated by the objective variational empowerment. Our work lays a novel foundation from which to evaluate, analyze, and develop representation learning techniques in goal-based RL.
  arXiv  Detail & Related papers  (2021-06-02T18:12:26Z)
• Dif-MAML: Decentralized Multi-Agent Meta-Learning [54.39661018886268]
  We propose a cooperative multi-agent meta-learning algorithm, referred to as MAML or Dif-MAML. We show that the proposed strategy allows a collection of agents to attain agreement at a linear rate and to converge to a stationary point of the aggregate MAML. Simulation results illustrate the theoretical findings and the superior performance relative to the traditional non-cooperative setting.
  arXiv  Detail & Related papers  (2020-10-06T16:51:09Z)
• Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning [90.93035276307239]
  We propose an information theoretic regularization objective and an annealing-based optimization method to achieve better generalization ability in RL agents. We demonstrate the extreme generalization benefits of our approach in different domains ranging from maze navigation to robotic tasks. This work provides a principled way to improve generalization in RL by gradually removing information that is redundant for task-solving.
  arXiv  Detail & Related papers  (2020-08-03T02:24:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.