Uncertainty Maximization in Partially Observable Domains: A Cognitive Perspective
Not on the map. Why?
Abstract (arXiv)
Faced with an ever-increasing complexity of their domains of application, artificial learning agents are now able to scale up in their ability to process an overwhelming amount of information coming from their interaction with an environment. However, this process of scaling does come with a cost of encoding and processing an increasing amount of redundant information that is not necessarily beneficial to the learning process itself. This work exploits the properties of the learning systems defined over partially observable domains by selectively focusing on the specific type of information that is more likely to express the causal interaction among the transitioning states of the environment. Adaptive masking of the observation space based on the temporal difference displacement criterion enabled a significant improvement in convergence of temporal difference algorithms defined over a partially observable Markov process.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 12 of its 91 references that are in the map. First posted on arXiv 22 Feb 2021.
Builds on
12 of 91 references.
References · 12
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2016OpenAI Gymcited by 1,684
- 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
- 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 457
- 2019DeepMDP: Learning Continuous Latent Space Models for Representation Learningcited by 204
- 2016Revisiting Active Perceptioncited by 90
- 2019Towards Interpretable Reinforcement Learning Using Attention Augmented Agentscited by 82
- 2018On Improving Deep Reinforcement Learning for POMDPscited by 49
- 2020Neuroevolution of Self-Interpretable Agentscited by 48
- 2014Online Planning Algorithms for POMDPscited by 42
- 2018Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processescited by 8
- 2019Influence-aware Memory Architectures for Deep Reinforcement Learningcited by 2
Built on by
Citing papers per year: 2021: 1.
1 paper.