Value Propagation Networks
By Nantas Nardelli, Gabriel Synnaeve, Zeming Lin, Pushmeet Kohli, Philip H. S. Torr, Nicolas Usunier. 2018
28 citations recorded by the source corpus.
We present Value Propagation (VProp), a set of parameter-efficient differentiable planning modules built on Value Iteration which can successfully be trained using reinforcement learning to solve unseen tasks, has the capability to generalize to larger map sizes, and can learn to navigate in dynamic environments. We show that the modules enable learning to plan when the environment also includes stochastic elements, providing a cost-efficient learning system to build low-level size-invariant planners for a variety of interactive navigation problems. We evaluate on static and dynamic configurations of MazeBase grid-worlds, with randomly generated environments of several different sizes, and on a StarCraft navigation scenario, with more complex dynamics, and pixels as input.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Tabish Rashid
- Christian Schröder de Witt
- Shimon Whiteson
- Tonghan Wang
- Gregory Farquhar
- Philip H. S. Torr
- Mikayel Samvelyan
- Georgios Papoudakis
Citations in the corpus
- The StarCraft Multi-Agent Challenge (2019, background): “…versions of the micromanagement tasks has thus been steadily appearing (Usunier et al., 2016; Foerster et al., 2017, 2018a; Rashid et al., 2018; Nardelli et al., 2018; Hu et al., 2018; Shao et al., 2018; Foerster et al., 2018b) with the release of TorchCraft (Synnaeve et al., 2016) and SC2LE…”
- The NetHack Learning Environment (2020, methodology): “Both StarCraft: BroodWar and StarCraft II have been successfully employed as RL environments [64, 69] for research on, for example, planning [52, 49], multi-agent systems [27, 63], imitation learning [70], and model-free reinforcement learning [70].”