Accuracy-based Curriculum Learning in Deep Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
In this paper, we investigate a new form of automated curriculum learning based on adaptive selection of accuracy requirements, called accuracy-based curriculum learning. Using a reinforcement learning agent based on the Deep Deterministic Policy Gradient algorithm and addressing the Reacher environment, we first show that an agent trained with various accuracy requirements sampled randomly learns more efficiently than when asked to be very accurate at all times. Then we show that adaptive selection of accuracy requirements, based on a local measure of competence progress, automatically generates a curriculum where difficulty progressively increases, resulting in a better learning efficiency than sampling randomly.
Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jun 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 3; 2023: 4; 2024: 0; 2025: 2; 2026: 3.
15 papers.
Sort:
By area:
- 2021Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use casescited by 39
- 2022Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptationcited by 28
- 2021A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learningcited by 21
- 2023Domain Randomization via Entropy Maximizationcited by 15
- 2022On Efficient Reinforcement Learning for Full-length Game of StarCraft IIcited by 14
- 2022Robust Reinforcement Learning via Genetic Curriculumcited by 10
- 2023Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skillscited by 8
- 2025MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spacescited by 7
- 2021Investigating Value of Curriculum Reinforcement Learning in Autonomous Driving Under Diverse Road and Weather Conditionscited by 3
- 2025Efficient Skill Discovery via Regret-Aware Optimizationcited by 3
- 2023CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learningcited by 2
- 2023Maneuver Decision-Making For Autonomous Air Combat Through Curriculum Learning And Reinforcement Learning With Sparse Rewardscited by 0
3 more
- 2026WINFlowNets: Warm-up Integrated Networks Training of Generative Flow Networks for Robotics and Machine Fault Adaptationcited by 0
- 2026Self Paced Gaussian Contextual Reinforcement Learningcited by 0
- 2026Scenario Generation for Risk-Aware Reinforcement Learning with Probably Approximately Safe Guaranteescited by 0
- 2026Scenario Generation for Risk-Aware Reinforcement Learning with Probably Approximately Safe Guarantees3 Jun 2026
- 2026Self Paced Gaussian Contextual Reinforcement Learning24 Mar 2026
- 2026WINFlowNets: Warm-up Integrated Networks Training of Generative Flow Networks for Robotics and Machine Fault Adaptation18 Mar 2026
- 2025Efficient Skill Discovery via Regret-Aware Optimization26 Jun 2025
- 2025MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces11 Feb 2025
- 2023Domain Randomization via Entropy Maximization3 Nov 2023
- 2023Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills30 Oct 2023
- 2023CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learning7 Apr 2023
- 2023Maneuver Decision-Making For Autonomous Air Combat Through Curriculum Learning And Reinforcement Learning With Sparse Rewards12 Feb 2023
- 2022Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation18 Oct 2022
- 2022On Efficient Reinforcement Learning for Full-length Game of StarCraft II23 Sep 2022
- 2022Robust Reinforcement Learning via Genetic Curriculum17 Feb 2022
3 more
- 2021Investigating Value of Curriculum Reinforcement Learning in Autonomous Driving Under Diverse Road and Weather Conditions14 Mar 2021
- 2021A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning25 Feb 2021
- 2021Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases23 Feb 2021
- 2021Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use casescited by 39
- 2022Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptationcited by 28
- 2021A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learningcited by 21
- 2023Domain Randomization via Entropy Maximizationcited by 15
- 2022On Efficient Reinforcement Learning for Full-length Game of StarCraft IIcited by 14
- 2022Robust Reinforcement Learning via Genetic Curriculumcited by 10
- 2023Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skillscited by 8
- 2025Efficient Skill Discovery via Regret-Aware Optimizationcited by 3
- 2023CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learningcited by 2
- 2023Maneuver Decision-Making For Autonomous Air Combat Through Curriculum Learning And Reinforcement Learning With Sparse Rewardscited by 0
- 2026WINFlowNets: Warm-up Integrated Networks Training of Generative Flow Networks for Robotics and Machine Fault Adaptationcited by 0
- 2026Self Paced Gaussian Contextual Reinforcement Learningcited by 0
12 most cited of 13 All 13 (JSON)
- 2026Scenario Generation for Risk-Aware Reinforcement Learning with Probably Approximately Safe Guarantees3 Jun 2026
- 2026Self Paced Gaussian Contextual Reinforcement Learning24 Mar 2026
- 2026WINFlowNets: Warm-up Integrated Networks Training of Generative Flow Networks for Robotics and Machine Fault Adaptation18 Mar 2026
- 2025Efficient Skill Discovery via Regret-Aware Optimization26 Jun 2025
- 2023Domain Randomization via Entropy Maximization3 Nov 2023
- 2023Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills30 Oct 2023
- 2023CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learning7 Apr 2023
- 2023Maneuver Decision-Making For Autonomous Air Combat Through Curriculum Learning And Reinforcement Learning With Sparse Rewards12 Feb 2023
- 2022Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation18 Oct 2022
- 2022On Efficient Reinforcement Learning for Full-length Game of StarCraft II23 Sep 2022
- 2022Robust Reinforcement Learning via Genetic Curriculum17 Feb 2022
- 2021A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning25 Feb 2021
12 newest of 13 All 13 (JSON)