Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
state_space_model [2018/02/14 19:45]
admin
state_space_model [2018/08/19 23:05]
admin
Line 18: Line 18:
  
 A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models. We show that carefully designed generative models that learn and operate on compact state representations,​ so-called state-space models, substantially reduce the computational costs for predicting outcomes of sequences of actions. Extensive experiments establish that state-space models accurately capture the dynamics of Atari games from the Arcade Learning Environment from raw pixels. The computational speed-up of state-space models while maintaining high accuracy makes their application in RL feasible: We demonstrate that agents which query these models for decision making outperform strong model-free baselines on the game MSPACMAN, demonstrating the potential of using learned environment models for planning. A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models. We show that carefully designed generative models that learn and operate on compact state representations,​ so-called state-space models, substantially reduce the computational costs for predicting outcomes of sequences of actions. Extensive experiments establish that state-space models accurately capture the dynamics of Atari games from the Arcade Learning Environment from raw pixels. The computational speed-up of state-space models while maintaining high accuracy makes their application in RL feasible: We demonstrate that agents which query these models for decision making outperform strong model-free baselines on the game MSPACMAN, demonstrating the potential of using learned environment models for planning.
 +
 +https://​arxiv.org/​abs/​1807.11929v1 Egocentric Spatial Memory
 +
 +https://​www.nature.com/​articles/​s41586-018-0102-6 Vector-based navigation using grid-like representations in artificial agents
 +