Corpus ID: 195069283

Unsupervised State Representation Learning in Atari

@article{Anand2019UnsupervisedSR,
  title={Unsupervised State Representation Learning in Atari},
  author={Ankesh Anand and Evan Racah and S. Ozair and Yoshua Bengio and Marc-Alexandre C{\^o}t{\'e} and R. Devon Hjelm},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.08226}
}
State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks. [...] Key Result Finally, we compare our technique with other state-of-the-art generative and contrastive representation learning methods.Expand
Benchmarking Unsupervised Representation Learning for Continuous Control
Evaluating Learned State Representations for Atari
  • Adam Tupper, K. Neshatian
  • Computer Science
  • 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ)
  • 2020
Latent World Models For Intrinsically Motivated Exploration
Return-Based Contrastive Representation Learning for Reinforcement Learning
Learning Markov State Abstractions for Deep Reinforcement Learning
Extracting Latent State Representations with Linear Dynamics from Rich Observations
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 92 REFERENCES
Representation Learning with Contrastive Predictive Coding
Wasserstein Dependency Measure for Representation Learning
Representation Learning: A Review and New Perspectives
Learning deep representations by mutual information estimation and maximization
Learning state representations with robotic priors
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
Playing Atari with Six Neurons
EMI: Exploration with Mutual Information
Multi-Object Representation Learning with Iterative Variational Inference
...
1
2
3
4
5
...