awesome-gcrl

This repo lists research papers on Goal-Conditioned Reinforcement Learning.

Research Papers

ICLR 2026

1. [Submitted to] Test-time Offline Reinforcement Learning on Goal-related Experience [Paper]

NeurIPS 2025

1. Hyper-GoalNet: Goal-Conditioned Manipulation Policy Learning with HyperNetworks

2. Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL [Paper]

3. 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities [Paper] [Code]

4. Offline Goal Conditioned Reinforcement Learning with Temporal Distance Representations

5. Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning [Paper]

6. GoalLadder: Incremental Goal Discovery with Vision-Language Models [Paper]

7. Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning [Paper]

8. Open-World Drone Active Tracking with Goal-Centered Rewards

9. Learning from Demonstrations via Capability-Aware Goal Sampling [Paper]

10. Horizon Reduction Makes Offline RL Scalable [Paper] [Code]

ICML 2025

1. Amy Zhang, Benjamin Eysenbach. [Tutorial] Generative AI Meets Reinforcement Learning. [Link]

2. Gong X, Yang S, Feng D, et al. Improving the Continuity of Goal-Achievement Ability via Policy Self-Regularization for Goal-Conditioned Reinforcement Learning[C]//Forty-second International Conference on Machine Learning. ICML, 2025. [Paper] [Code]

3. Ke K, Lin Q, Liu Z, et al. Conservative Offline Goal-Conditioned Implicit V-Learning[C]//Forty-second International Conference on Machine Learning. [Paper]

4. He J, Li K, Zang Y, et al. Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning[C]//Forty-second International Conference on Machine Learning. [Paper]

5. Richens J, Everitt T, Abel D. General agents need world models[C]//Forty-second International Conference on Machine Learning. [Paper]

6. Wang V H, Wang T, Pajarinen J. Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals[C]//Forty-second International Conference on Machine Learning. [Paper]

7. Gaven L, Carta T, ROMAC C, et al. MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces[C]//Forty-second International Conference on Machine Learning. [Paper]

8. Lo C, Roice K, Panahi P M, et al. Goal-space planning with subgoal models[J]. Journal of Machine Learning Research, 2024, 25(330): 1-57. [Paper]

9. Baek S, Park J, Oh S, et al. Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning[C]//Forty-second International Conference on Machine Learning. [Paper]

ICLR 2025

1. Gong X, Feng D, Xu K, et al. VVC-Gym: A Fixed-Wing UAV Reinforcement Learning Environment for Multi-Goal Long-Horizon Problems[C]//The Thirteenth International Conference on Learning Representations. [Paper] [Code]

2. Park S, Frans K, Eysenbach B, et al. Ogbench: Benchmarking offline goal-conditioned rl[C]//The Thirteenth International Conference on Learning Representations. [Paper] [Code]

3. Bortkiewicz M, Pałucki W, Myers V, et al. Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research[C]//The Thirteenth International Conference on Learning Representations. [Paper] [Code]

4. Chuck C, Feng F, Qi C, et al. Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning[C]//The Thirteenth International Conference on Learning Representations. [Paper]

5. Luo Y, Du Y. Grounding Video Models to Actions through Goal Conditioned Exploration[C]//The Thirteenth International Conference on Learning Representations. [Paper]

6. Myers V, Ji C, Eysenbach B. Horizon Generalization in Reinforcement Learning[C]//The Thirteenth International Conference on Learning Representations. [Paper]

NeurIPS 2024

1. Gong X, Feng D, Xu K, et al. Goal-Conditioned On-Policy Reinforcement Learning[C]//The Thirty-eighth Annual Conference on Neural Information Processing Systems. 2024. [Paper] [Code]

2. Duan Y, Cui G, Zhu H. Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning[C]//The Thirty-eighth Annual Conference on Neural Information Processing Systems. 2024. [Paper]

3. Cheng H, Brown J W. Goal Reduction with Loop-Removal Accelerates RL and Models Human Brain Activity in Goal-Directed Learning[C]//The Thirty-eighth Annual Conference on Neural Information Processing Systems. 2024. [Paper]

4. Yalcinkaya B, Lauffer N, Vazquez-Chanlatte M, et al. Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning[C]//The Thirty-eighth Annual Conference on Neural Information Processing Systems. 2024. [Paper]

5. Wu J, Wang Y, Li L, et al. Goal Conditioned Reinforcement Learning for Photo Finishing Tuning[C]//The Thirty-eighth Annual Conference on Neural Information Processing Systems. 2024. [Paper]

6. Molinaro G, Colas C, Oudeyer P Y, et al. Latent learning progress drives autonomous goal selection in human reinforcement learning[J]. Advances in Neural Information Processing Systems, 2024, 37: 32251-32280. [Paper]

7. Nath V, Slack D, Da J, et al. Learning goal-conditioned representations for language reward models[J]. Advances in Neural Information Processing Systems, 2024, 37: 117070-117108. [Paper]

8. Duan Y, Mao W, Zhu H. Learning world models for unconstrained goal navigation[J]. Advances in Neural Information Processing Systems, 2024, 37: 59236-59265. [Paper]

9. Fan Y, Li J, Swaminathan A, et al. How to solve contextual goal-oriented problems with offline datasets?[J]. Advances in Neural Information Processing Systems, 2024, 37: 99433-99463. [Paper]

ICML 2024

1. Zheng S, Bai C, Yang Z, et al. How Does Goal Relabeling Improve Sample Efficiency?[C]//Forty-first International Conference on Machine Learning. 2024. [Paper]

2. Wang V H, Wang T, Yang W, et al. Probabilistic subgoal representations for hierarchical reinforcement learning[C]//Forty-first International Conference on Machine Learning. 2024. [Paper]

3. Jain V, Ravanbakhsh S. Learning to Reach Goals via Diffusion[C]//Forty-first International Conference on Machine Learning. 2024. [Paper]

4. Na H, Moon I. LAGMA: LAtent Goal-guided Multi-Agent Reinforcement Learning[C]//Forty-first International Conference on Machine Learning. 2024. [Paper]

5. Myers V, Zheng C, Dragan A, et al. Learning temporal distances: contrastive successor features can provide a metric structure for decision-making[C]//Forty-first International Conference on Machine Learning. 2024. 37076-37096. [Paper]

6. Xudong G, Dawei F, Xu K, et al. "Iterative Regularized Policy Optimization with Imperfect Demonstrations." Forty-first International Conference on Machine Learning. 2024. [Paper] [Code]

ICLR 2024

1. Zheng C, Eysenbach B, Walke H R, et al. Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data[C]//The Twelfth International Conference on Learning Representations. [Paper]

ICLR 2023

1. Zhu D, Li L E, Elhoseiny M. Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning[C]//The Eleventh International Conference on Learning Representations. [Paper]

NeurIPS 2019

1. Eysenbach B, Salakhutdinov R R, Levine S. Search on the replay buffer: Bridging planning and reinforcement learning[J]. Advances in neural information processing systems, 2019, 32. [Paper]

GCRL environments

1. Gong X, Feng D, Xu K, et al. VVC-Gym: A Fixed-Wing UAV Reinforcement Learning Environment for Multi-Goal Long-Horizon Problems[C]//International Conference on Learning Representations. ICLR, 2025. [Paper] [Code]

2. Gymnasium-Robotics. [Code]

3. Gallouédec Q, Cazin N, Dellandréa E, et al. panda-gym: Open-source goal-conditioned environments for robotic learning[C]//4th Robot Learning Workshop: Self-Supervised and Lifelong Learning@ NeurIPS 2021. 2021. [Paper] [Code]

4. Park S, Frans K, Eysenbach B, et al. Ogbench: Benchmarking offline goal-conditioned rl[C]//International Conference on Learning Representations. ICLR, 2025. [Paper] [Code]

5. Bortkiewicz M, Pałucki W, Myers V, et al. Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research[C]//The Thirteenth International Conference on Learning Representations. [Paper] [Code]

6. Plappert M, Andrychowicz M, Ray A, et al. Multi-goal reinforcement learning: Challenging robotics environments and request for research[J]. arxiv preprint arxiv:1802.09464, 2018. [Paper]