mlsanityData to 14 Oct 2026

Adaptive Correlation-Weighted Intrinsic Rewards for Reinforcement Learning

arXiv 2602.24081 ↗First posted 27 Feb 2026cs.LG cs.AIcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

We propose ACWI (Adaptive Correlation Weighted Intrinsic), an adaptive intrinsic reward scaling framework designed to dynamically balance intrinsic and extrinsic rewards for improved exploration in sparse reward reinforcement learning. Unlike conventional approaches that rely on manually tuned scalar coefficients, which often result in unstable or suboptimal performance across tasks, ACWI learns a state dependent scaling coefficient online. Specifically, ACWI introduces a lightweight Beta Network that predicts the intrinsic reward weight directly from the agent state through an encoder based architecture. The scaling mechanism is optimized using a correlation based objective that encourages alignment between the weighted intrinsic rewards and discounted future extrinsic returns. This formulation enables task adaptive exploration incentives while preserving computational efficiency and training stability. We evaluate ACWI on a suite of sparse reward environments in MiniGrid. Experimental results demonstrate that ACWI consistently improves sample efficiency and learning stability compared to fixed intrinsic reward baselines, achieving superior performance with minimal computational overhead.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 18 of its 27 references that are in the map. First posted on arXiv 27 Feb 2026.

Builds on

18 of 27 references.

References · 18

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  4. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  5. 2018Exploration by Random Network Distillationcited by 993
  6. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
  7. 2016Reinforcement Learning with Unsupervised Auxiliary Taskscited by 404
  8. 2016#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learningcited by 309
  9. 2020Agent57: Outperforming the Atari Human Benchmarkcited by 303
  10. 2017Count-Based Exploration with Neural Density Modelscited by 257
  11. 2020Never Give Up: Learning Directed Exploration Strategiescited by 212
  12. 2018An Introduction to Deep Reinforcement Learningcited by 206
6 more
  1. 2016Learning to Navigate in Complex Environmentscited by 198
  2. 2020RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environmentscited by 135
  3. 2021On Bonus-Based Exploration Methods in the Arcade Learning Environmentcited by 37
  4. 2022Redeeming Intrinsic Rewards via Constrained Optimizationcited by 24
  5. 2023Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learningcited by 12
  6. 2020A Self-Tuning Actor-Critic Algorithmcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025LLM-Driven Intrinsic Motivation for Sparse Reward Reinforcement Learning
  2. 2026Intrinsic Reward Policy Optimization for Sparse-Reward Environments
  3. 2026Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization
  4. 2024Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations
  5. 2025MIR: Efficient Exploration in Episodic Multi-Agent Reinforcement Learning via Mutual Intrinsic Reward
  6. 2026Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning
  7. 2025Deep Reinforcement Learning with Hybrid Intrinsic Reward Model
  8. 2024AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learning