Built on

Friston, K., Trujillo-Barreto, N., Daunizeau, J.: Dem: a variational treatment of dynamic systems. NeuroImage 41
2008
Earlier work this paper cites.
Friston, K.J., Daunizeau, J., Kilner, J., Kiebel, S.J.: Action and behavior: a free-energy formulation. Biol Cybern 102
2010
Earlier work this paper cites.
Friston, K.J.: The free-energy principle: a unified brain theory? Nature 11
2010
Earlier work this paper cites.
Adams, R.A., Shipp, S., Friston, K.J.: Predictions not commands: active inference in the motor system. Brain Struct Funct. 218
2012
Earlier work this paper cites.
Friston, K.J., Samothrakis, S., Montague, R.: Active inference and agency: optimal control without cost functions. Biol Cybern 106
2012
Earlier work this paper cites.
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv Prepr. arXiv:1312.5602v1 (2013)
Original
2013
Earlier work this paper cites.

Similar

Hausknecht, M., Stone, P.: Deep recurrent q-learning for partially observable mdps. In: AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents (AAAI-SDMIA15) (November 2015)
2015
Cited alongside, same era.
Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: Deep reinforcement learning: A brief survey. IEEE Signal Processing Magazine 34
2017
Cited alongside, same era.
Ueltzhöffer, K.: Deep active inference. Biological Cybernetics 112
2018
Cited alongside, same era.
Sancaktar, C., Lanillos, P.: End-to-end pixel-based deep active inference for body perception and action. arXiv preprint arXiv:2001.05847 (2019)
Original
2019
Cited alongside, same era.
Tschantz, A., Baltieri, M., Seth, A.K., Buckley, C.L.: Scaling active inference. arXiv Prepr. arXiv:1911.10601v1 (2019)
Original

Then

Parr, T., Friston, K.J.: Generalised free energy and active inference. Biol Cybern 113
2019
Later among the works it cites.
Millidge, B.: Deep active inference as variational policy gradients. Journal of Mathematical Psychology 96
2020
Closest in time.
Çatal, O., Wauthier, S., Verbelen, T., Boom, C.D., Dhoedt, B.: Deep active inference for autonomous robot navigation. arXiv Prepr. arXiv:2003.03220v1 (2020)
Original
2020
Closest in time.
Fountas, Z., Sajid, N., Mediano, P.A.M., Friston, K.: Deep active inference agents using monte-carlo methods. arXiv Prepr. arXiv:2006.04176v1 (2020)
Original
2020
Closest in time.
Lanillos, P., Pages, J., Cheng, G.: Robot self/other distinction: active inference meets neural networks learning in a mirror. In: Proceedings of the 24th European Conference on Artificial Intelligence (ECAI). pp. 2410 – 2416 (2020). https://doi.org/10.3233/FAIA200372

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2020

Deep Active Inference for Partially Observable MDPs

van der Himst, Otto, Lanillos, Pablo

Understand

Deep active inference has been proposed as a scalable approach to perception and action that deals with large policy and state spaces.

However, current models are limited to fully observable domains.
In this paper, we describe a deep active inference model that can learn successful policies directly from high-dimensional sensory inputs.
The deep learning architecture optimizes a variant of the expected free energy and encodes the continuous state representation by means of a variational autoencoder.

Built on

Friston, K., Trujillo-Barreto, N., Daunizeau, J.: Dem: a variational treatment of dynamic systems. NeuroImage 41
2008
Earlier work this paper cites.
Friston, K.J., Daunizeau, J., Kilner, J., Kiebel, S.J.: Action and behavior: a free-energy formulation. Biol Cybern 102
2010
Earlier work this paper cites.
Friston, K.J.: The free-energy principle: a unified brain theory? Nature 11
2010
Earlier work this paper cites.
Adams, R.A., Shipp, S., Friston, K.J.: Predictions not commands: active inference in the motor system. Brain Struct Funct. 218
2012
Earlier work this paper cites.
Friston, K.J., Samothrakis, S., Montague, R.: Active inference and agency: optimal control without cost functions. Biol Cybern 106
2012
Earlier work this paper cites.
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv Prepr. arXiv:1312.5602v1 (2013)
Original
2013
Earlier work this paper cites.

Similar

Hausknecht, M., Stone, P.: Deep recurrent q-learning for partially observable mdps. In: AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents (AAAI-SDMIA15) (November 2015)
2015
Cited alongside, same era.
Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: Deep reinforcement learning: A brief survey. IEEE Signal Processing Magazine 34
2017
Cited alongside, same era.
Ueltzhöffer, K.: Deep active inference. Biological Cybernetics 112
2018
Cited alongside, same era.
Sancaktar, C., Lanillos, P.: End-to-end pixel-based deep active inference for body perception and action. arXiv preprint arXiv:2001.05847 (2019)
Original
2019
Cited alongside, same era.
Tschantz, A., Baltieri, M., Seth, A.K., Buckley, C.L.: Scaling active inference. arXiv Prepr. arXiv:1911.10601v1 (2019)
Original

Then

Parr, T., Friston, K.J.: Generalised free energy and active inference. Biol Cybern 113
2019
Later among the works it cites.
Millidge, B.: Deep active inference as variational policy gradients. Journal of Mathematical Psychology 96
2020
Closest in time.
Çatal, O., Wauthier, S., Verbelen, T., Boom, C.D., Dhoedt, B.: Deep active inference for autonomous robot navigation. arXiv Prepr. arXiv:2003.03220v1 (2020)
Original
2020
Closest in time.
Fountas, Z., Sajid, N., Mediano, P.A.M., Friston, K.: Deep active inference agents using monte-carlo methods. arXiv Prepr. arXiv:2006.04176v1 (2020)
Original
2020
Closest in time.
Lanillos, P., Pages, J., Cheng, G.: Robot self/other distinction: active inference meets neural networks learning in a mirror. In: Proceedings of the 24th European Conference on Artificial Intelligence (ECAI). pp. 2410 – 2416 (2020). https://doi.org/10.3233/FAIA200372

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

2019

Cited alongside, same era.

Oliver, G., Lanillos, P., Cheng, G.: Active inference body perception and action for humanoid robots. arXiv Prepr. arXiv:1906.03022v3 (2019)

Original

2019

Cited alongside, same era.

Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., Petersen, S., Sadik, C.B.A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518

Cited in the paper.

2020

Closest in time.

Rood, T., van Gerven, M., Lanillos, P.: A deep active inference model of the rubber-hand illusion. arXiv Prepr. arXiv:2008.07408 (2020)

Original

2020

Closest in time.