mlsanityData to 14 Oct 2026

Deep Reinforcement Learning with Hybrid Intrinsic Reward Model

arXiv 2501.12627 ↗First posted 22 Jan 2025cs.LGcited by 1

On the map: LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF

Abstract (arXiv)

Intrinsic reward shaping has emerged as a prevalent approach to solving hard-exploration and sparse-rewards environments in reinforcement learning (RL). While single intrinsic rewards, such as curiosity-driven or novelty-based methods, have shown effectiveness, they often limit the diversity and efficiency of exploration. Moreover, the potential and principle of combining multiple intrinsic rewards remains insufficiently explored. To address this gap, we introduce HIRE (Hybrid Intrinsic REward), a flexible and elegant framework for creating hybrid intrinsic rewards through deliberate fusion strategies. With HIRE, we conduct a systematic analysis of the application of hybrid intrinsic rewards in both general and unsupervised RL across multiple benchmarks. Extensive experiments demonstrate that HIRE can significantly enhance exploration efficiency and diversity, as well as skill acquisition in complex and dynamic settings.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 6 of its 46 references that are in the map. First posted on arXiv 22 Jan 2025.

Builds on

6 of 46 references.

References · 6

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2016Variational Intrinsic Controlcited by 267
  3. 2015Incentivizing Exploration In Reinforcement Learning With Deep Predictive Modelscited by 154
  4. 2022Lipschitz-constrained Unsupervised Skill Discoverycited by 62
  5. 2023A Study of Global and Episodic Bonuses for Exploration in Contextual MDPscited by 20
  6. 2024RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learningcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learningcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2026Intrinsic Reward Policy Optimization for Sparse-Reward Environments
  2. 2025The impact of intrinsic rewards on exploration in Reinforcement Learning
  3. 2025Autonomous state-space segmentation for Deep-RL sparse reward scenarios
  4. 2024Fostering Intrinsic Motivation in Reinforcement Learning with Pretrained Foundation Models
  5. 2024Combining Automated Optimisation of Hyperparameters and Reward Shape
  6. 2024Effective Reward Specification in Deep Reinforcement Learning
  7. 2026Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization
  8. 2026Adaptive Correlation-Weighted Intrinsic Rewards for Reinforcement Learning