mlsanityData to 7 Oct 2026

Dealing with Sparse Rewards in Reinforcement Learning

arXiv 1910.09281 ↗First posted 21 Oct 2019cs.LG cs.AI stat.MLcited by 40

Not on the map. Why?

Abstract (arXiv)

Successfully navigating a complex environment to obtain a desired outcome is a difficult task, that up to recently was believed to be capable only by humans. This perception has been broken down over time, especially with the introduction of deep reinforcement learning, which has greatly increased the difficulty of tasks that can be automated. However, for traditional reinforcement learning agents this requires an environment to be able to provide frequent extrinsic rewards, which are not known or accessible for many real-world environments. This project aims to explore and contrast existing reinforcement learning solutions that circumnavigate the difficulties of an environment that provide sparse rewards. Different reinforcement solutions will be implemented over a several video game environments with varying difficulty and varying frequency of rewards, as to properly investigate the applicability of these solutions. This project introduces a novel reinforcement learning solution by combining aspects of two existing state of the art sparse reward solutions, curiosity driven exploration and unsupervised auxiliary tasks.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 2; 2023: 6; 2024: 11; 2025: 7; 2026: 10.

40 papers.

Sort:

By area:

  1. 2023Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalizationcited by 140
  2. 2024A Survey on Self-Evolution of Large Language Modelscited by 86
  3. 2024Code as Reward: Empowering Reinforcement Learning with VLMscited by 38
  4. 2021ScheduleNet: Learn to solve multi-agent scheduling problems with reinforcement learningcited by 31
  5. 2025Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewardscited by 29
  6. 2025Fine-Grained GRPO for Precise Preference Alignment in Flow Modelscited by 21
  7. 2023Behavior Alignment via Reward Function Optimizationcited by 16
  8. 2025SCAR: Shapley Credit Assignment for More Efficient RLHFcited by 13
  9. 2024Efficient Diversity-based Experience Replay for Deep Reinforcement Learningcited by 7
  10. 2021A Reinforcement Learning Approach to Parameter Selection for Distributed Optimal Power Flowcited by 5
  11. 2021Discovering and Exploiting Sparse Rewards in a Learned Behavior Spacecited by 5
  12. 2024Exploratory Optimal Stopping: A Singular Control Formulationcited by 5
28 more
  1. 2026Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?cited by 5
  2. 2022Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?cited by 4
  3. 2024Take a Step and Reconsider: Sequence Decoding for Self-Improved Neural Combinatorial Optimizationcited by 4
  4. 2024Automated Rewards via LLM-Generated Progress Functionscited by 4
  5. 2026Learning to Disprove: Formal Counterexample Generation with Large Language Modelscited by 4
  6. 2021Goal-constrained Sparse Reinforcement Learning for End-to-End Drivingcited by 3
  7. 2024Feasibility Consistent Representation Learning for Safe Reinforcement Learningcited by 3
  8. 2025VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RLcited by 3
  9. 2023Collaborative Route Planning of UAVs, Workers and Cars for Crowdsensing in Disaster Responsecited by 2
  10. 2025From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learningcited by 2
  11. 2026Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specificationscited by 2
  12. 2022WILD-SCAV: Benchmarking FPS Gaming AI on Unity3D-based Environmentscited by 1
  13. 2023Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIscited by 1
  14. 2024On shallow planning under partial observabilitycited by 1
  15. 2026World Models as an Intermediary between Agents and the Real Worldcited by 1
  16. 2026STAIR: Effective Incident Response Using an End-to-End Agentic Planning Frameworkcited by 1
  17. 2023Deep Reinforcement Learning for mmWave Initial Beam Alignmentcited by 0
  18. 2023Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigationcited by 0
  19. 2024Enhancing Heterogeneous Multi-Agent Cooperation in Decentralized MARL via GNN-driven Intrinsic Rewardscited by 0
  20. 2024AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learningcited by 0
  21. 2024SNN-Based Online Learning of Concepts and Action Laws in an Open Worldcited by 0
  22. 2025SparseMap: A Sparse Tensor Accelerator Framework Based on Evolution Strategycited by 0
  23. 2025ARAC: Adaptive Regularized Multi-Agent Soft Actor-Critic in Graph-Structured Adversarial Gamescited by 0
  24. 2026Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purificationcited by 0
  25. 2026Heterogeneous Vertiport Selection Optimization for On-Demand Air Taxi Services: A Deep Reinforcement Learning Approachcited by 0
  26. 2026Mesh-RL: Coupled subgrid reinforcement learningcited by 0
  27. 2026From LLM-Generated Specifications to Learned Quadruped Locomotioncited by 0
  28. 2026iADD: Improving Alignment and Diversity in Diffusion Policy Optimizationcited by 0