More Like this

1. Planning with Abstract Learned Models While Learning Transferable Subtasks

   https://doi.org/10.1609/aaai.v34i06.6555  

   Winder, John; Milani, Stephanie; Landen, Matthew; Oh, Erebus; Parr, Shane; Squire, Shawn; desJardins, Marie; Matuszek, Cynthia (February 2020, Proceedings of the AAAI Conference on Artificial Intelligence)

   We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this framework Planning with Abstract Learned Models (PALM). By representing subtasks symbolically using a new formal structure, the lifted abstract Markov decision process (L-AMDP), PALM learns models that are independent and modular. Through our experiments, we show how PALM integrates planning and execution, facilitating a rapid and efficient learning of abstract, hierarchical models. We also demonstrate the increased potential for learned models to be transferred to new and related tasks. 

   more » « less
2. Planning with Abstract Learned Models While Learning Transferable Subtasks

   Winder, John; Milani, Stephanie; Landen, Matthew; Oh, Erebus; Parr, Shane; Squire, Shawn; desJardins, Marie; Matuszek, Cynthia (February 2020, Proceedings of the AAAI Conference on Artificial Intelligence)

   null (Ed.)

   We introduce an algorithm for model-based hierarchical reinforcement learning to acquire self-contained transition and reward models suitable for probabilistic planning at multiple levels of abstraction. We call this framework Planning with Abstract Learned Models (PALM). By representing subtasks symbolically using a new formal structure, the lifted abstract Markov decision process (L-AMDP), PALM learns models that are independent and modular. Through our experiments, we show how PALM integrates planning and execution, facilitating a rapid and efficient learning of abstract, hierarchical models. We also demonstrate the increased potential for learned models to be transferred to new and related tasks. 

   more » « less
3. Using Deep Learning to Bootstrap Abstractions for Robot Planning

   Shah, Naman; Srivastava, Siddharth (May 2022, Proceedings of the International Conference on Autonomous Agents)

   This paper addresses the problem of learning abstractions that boost robot planning performance while providing strong guarantees of reliability. Although state-of-the-art hierarchical robot planning algorithms allow robots to efficiently compute long-horizon motion plans for achieving user desired tasks, these methods typically rely upon environment-dependent state and action abstractions that need to be hand-designed by experts. We present a new approach for bootstrapping the entire hierarchical planning process. This allows us to compute abstract states and actions for new environments automatically using the critical regions predicted by a deep neural network with an auto-generated robot-specific architecture. We show that the learned abstractions can be used with a novel multi-source bi-directional hierarchical robot planning algorithm that is sound and probabilistically complete. An extensive empirical evaluation on twenty different settings using holonomic and non-holonomic robots shows that (a) our learned abstractions provide the information necessary for efficient multi-source hierarchical planning; and that (b) this approach of learning, abstractions, and planning outperforms state-of-the-art baselines by nearly a factor of ten in terms of planning time on test environments not seen during training. 

   more » « less
4. Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning

   Shah, Naman; Srivastava, Siddharth (May 2022, International Conference on Autonomous Agents and Multiagent Systems)

   Pelachaud, Catherine; Taylor, Matthew E.; Mascardi, Viviana (Ed.)

   This paper addresses the problem of learning abstractions that boost robot planning performance while providing strong guarantees of reliability. Although state-of-the-art hierarchical robot planning algorithms allow robots to efficiently compute long-horizon motion plans for achieving user desired tasks, these methods typically rely upon environment-dependent state and action abstractions that need to be hand-designed by experts. We present a new approach for bootstrapping the entire hierarchical planning process. This allows us to compute abstract states and actions for new environments automatically using the critical regions predicted by a deep neural network with an auto-generated robot-specific architecture. We show that the learned abstractions can be used with a novel multi-source bi-directional hierarchical robot planning algorithm that is sound and probabilistically complete. An extensive empirical evaluation on twenty different settings using holonomic and non-holonomic robots shows that (a) our learned abstractions provide the information necessary for efficient multi-source hierarchical planning; and that (b) this approach of learning, abstractions, and planning outperforms state-of-the-art baselines by nearly a factor of ten in terms of planning time on test environments not seen during training. 

   more » « less
5. Universal Planning Networks

   Srinivas, A.; Jabri, A.; Abbeel, P.; Levine, S.; Finn, C. (January 2018, International Conference on Machine Learning (ICML))

   A key challenge in complex visuomotor control is learning abstract representations that are ef- fective for specifying goals, planning, and gen- eralization. To this end, we introduce universal planning networks (UPN). UPNs embed differen- tiable planning within a goal-directed policy. This planning computation unrolls a forward model in a latent space and infers an optimal action plan through gradient descent trajectory optimization. The plan-by-gradient-descent process and its un- derlying representations are learned end-to-end to directly optimize a supervised imitation learning objective. We find that the representations learned are not only effective for goal-directed visual imi- tation via gradient-based trajectory optimization, but can also provide a metric for specifying goals using images. The learned representations can be leveraged to specify distance-based rewards to reach new target states for model-free reinforce- ment learning, resulting in substantially more ef- fective learning when solving new tasks described via image-based goals. We were able to achieve successful transfer of visuomotor planning strate- gies across robots with significantly different mor- phologies and actuation capabilities. 

   more » « less