Publications

2026

1. ICAPS

   GammaZero: Learning to Guide Belief-Space Search for Long-Horizon POMDPs with Generalizable Graph Representations

   Rajesh Mangannavar, and Prasad Tadepalli

   In International Conference on Automated Planning and Scheduling (ICAPS), 2026

   Website

2025

1. NeurIPS SpaVLE

   Hierarchical Object-Oriented POMDP Planning for Object Rearrangement

   Rajesh Mangannavar, Alan Fern, and Prasad Tadepalli

   In NeurIPS Workshop on Spatial Vision and Language Embodiment (SpaVLE), 2025

   PDF Website
2. NeurIPS

   Graph Neural Network Based Action Ranking for Planning

   Rajesh Mangannavar, Stefan Lee, Alan Fern, and 1 more author

   In Advances in Neural Information Processing Systems (NeurIPS), 2025

   PDF Website
3. Arxiv

   Planning with affordances: Integrating learned affordance models and symbolic planning

   Rajesh Mangannavar

   arXiv preprint arXiv:2502.02768, 2025

   PDF

2019

1. ISNN

   Learning Agents with Prioritization and Parameter Noise in Continuous State and Action Space

   R. Mangannavar, and G. Srinivasaraghavan

   Advances in Neural Networks – ISNN, 2019

   Abs DOI HTML PDF

   Among the many variants of RL, an important class of problems is where the state and action spaces are continuous—autonomous robots, autonomous vehicles, optimal control are all examples of such problems that can lend themselves naturally to reinforcement based algorithms, and have continuous state and action spaces. In this paper, we introduce a prioritized form of a combination of state-of-the-art approaches such as Deep Q-learning (DQN) and Deep Deterministic Policy Gradient (DDPG) to outperform the earlier results for continuous state and action space problems. Our experiments also involve the use of parameter noise during training resulting in more robust deep RL models outperforming the earlier results significantly. We believe these results are a valuable addition for continuous state and action space problems.