Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization

• URL: http://arxiv.org/abs/2605.30928v1
• Date: Fri, 29 May 2026 07:18:20 GMT
• Title: Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization
• Abstract summary: We introduce a novel human-like reinforcement learning framework that predicts action sequences closely aligned with human behaviors.<n>We encode human demonstrations into macro actions using a hierarchical macro action quantization approach (termed HiMAQ)
• Score: 5.162898227762136
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human-like agents are a long-standing goal of artificial intelligence. Despite strong performance, most reinforcement learning (RL) agents remain reward-driven and often exhibit behaviors that differ from humans, limiting interpretability and reliability. In this work, we introduce a novel human-like RL framework that predicts action sequences closely aligned with human behaviors while maximizing rewards. Specifically, we encode human demonstrations into macro actions using a hierarchical macro action quantization approach (termed HiMAQ) consisting of two successive levels of vector quantization. The lower quantization level maps input actions to fine-grained subaction clusters, while the higher quantization level aggregates these subaction clusters into action clusters. Extensive evaluations on the D4RL benchmarks show that our hierarchical approach outperforms the non-hierarchical baseline (MAQ), achieving better human-likeness scores while maintaining comparable or better success rates than previous RL agents. The improvements generalize across integrations with various RL algorithms, namely IQL, SAC, and RLPD.

Related papers

• A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics [6.4420182172671865]
  We present a novel hierarchical action tokenizer for incontext- imitation learning, namely HiST-AT. Specifically, our hierarchical-temporal approach conducts multi-level clustering, while simultaneously recovering input actions and their associated timestamps cues.
  arXiv  Detail & Related papers  (2026-04-16T16:47:08Z)
• HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents [19.63866851076813]
  HiMAC is a hierarchical agentic RL framework that decomposes long-horizon decision-making into macro-level planning and micro-level execution.<n>Our results show that introducing structured hierarchy, rather than increasing model scale alone, is a key factor for enabling robust long-horizon agentic intelligence.
  arXiv  Detail & Related papers  (2026-03-01T08:09:03Z)
• Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective [85.06838178922791]
  Reinforcement Learning (RL) has proven highly effective for autoregressive language models.<n>But adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges.<n>We propose a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy.
  arXiv  Detail & Related papers  (2025-12-03T13:05:32Z)
• Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization [20.732922711530527]
  We introduce Macro Action Quantization (MAQ), a human-like reinforcement learning framework that distills human demonstrations into macro actions.<n>Experiments on D4RL Adroit benchmarks show that MAQ significantly improves human-likeness, increasing trajectory similarity scores, and achieving the highest human-likeness rankings among all RL agents.<n>Our results also demonstrate that MAQ can be easily integrated into various off-the-shelf RL algorithms, opening a promising direction for learning human-like RL agents.
  arXiv  Detail & Related papers  (2025-11-19T02:59:47Z)
• Feature Identification for Hierarchical Contrastive Learning [7.655211354400059]
  We propose two novel hierarchical contrastive learning (HMLC) methods.<n>Our approach explicitly models inter-class relationships and imbalanced class distribution at higher hierarchy levels.<n>Our method achieves state-of-the-art performance in linear evaluation, outperforming existing hierarchical contrastive learning methods by 2 percentage points in terms of accuracy.
  arXiv  Detail & Related papers  (2025-10-01T12:46:47Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning [56.496001894673235]
  Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs)<n>Our analysis reveals that puzzling phenomena like aha moments", length-scaling'' and entropy dynamics are not disparate occurrences but hallmarks of an emergent reasoning hierarchy.
  arXiv  Detail & Related papers  (2025-09-03T18:52:49Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Robot Learning [62.3886343725955]
  We introduce a novel value-based reinforcement learning algorithm that learns a critic network that outputs Q-values over a sequence of actions.<n>Experiments show that CQN-AS outperforms several baselines on a variety of sparse-reward humanoid control and tabletop manipulation tasks.
  arXiv  Detail & Related papers  (2024-11-19T01:23:52Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability [67.8426046908398]
  Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world. This paper presents MetaPG, an evolutionary method for automated design of actor-critic loss functions.
  arXiv  Detail & Related papers  (2022-04-08T20:46:16Z)

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.