Automatic Curriculum Learning Through Value Disagreement in Reinforcement Learning

References

1. Zhang, Abbeel, Pinto — Automatic Curriculum Learning through Value Disagreement, NeurIPS 2020. arXiv · PDF
2. Bengio, Louradour, Collobert, Weston — Curriculum Learning, 2009. Scholar
3. Florensa, Held, Geng, Abbeel — Automatic Goal Generation for RL Agents (Goal GAN), 2018. arXiv 1705.06366
4. Matiisen, Oliver, Cohen, Schulman — Teacher-Student Curriculum Learning, 2017. arXiv 1707.00183
5. Portelas, Colas, Weng, Hofmann, Oudeyer — Automatic Curriculum Learning for Deep RL: A Short Survey, 2020. arXiv 2003.04664
6. Schaul, Horgan, Gregor, Silver — Universal Value Function Approximators, 2015. Scholar
7. Andrychowicz et al. — Hindsight Experience Replay, NeurIPS 2017. arXiv 1707.01495
8. Plappert et al. — Multi-Goal RL: Challenging Robotics Environments and Request for Research, 2018. arXiv 1802.09464
9. Liu, Zhu, Zhang — Goal-Conditioned RL: Problems and Solutions, IJCAI survey 2022. arXiv 2201.08299
10. Portelas, Colas, Hofmann, Oudeyer — Teacher algorithms for curriculum learning of deep RL in continuously parameterized environments, 2019. arXiv 1910.07224
11. Pathak, Gandhi, Gupta — Self-Supervised Exploration via Disagreement, 2019. arXiv 1906.04161
12. Osband, Blundell, Pritzel, Van Roy — Deep Exploration via Bootstrapped DQN, 2016. arXiv 1602.04621
13. Lakshminarayanan, Pritzel, Blundell — Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles, 2017. arXiv 1612.01474
14. Sukhbaatar et al. — Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play, 2018. arXiv 1703.05407
15. Jiang, Grefenstette, Rocktäschel — Prioritized Level Replay, 2021. arXiv 2010.03934
16. Baker et al. — Emergent Tool Use From Multi-Agent Autocurricula, 2019. arXiv 1909.07528
17. Wang, Lehman, Clune, Stanley — POET, 2019. arXiv 1901.01753 · Dennis et al. — PAIRED, 2020. arXiv 2012.02096
18. Yu et al. — DAPO: An Open-Source LLM RL System at Scale, 2025. arXiv 2503.14476