Sam Mady

Research @Mila_Quebec and @MPI_IS Robotics MSC @ETH_en

[Sam Mady @sam_s_mady]

CausalWorld is an open-source simulation framework and benchmark for causal structure and transfer learning in a robotic manipulation environment where tasks range from rather simple to extremely hard. Work done at @MPI_IS and @MILAMontreal. (1/9)

https://t.co/86G08g7izy

[Sam Mady @sam_s_mady]

Great work from @mayankm155 and @NVIDIAAI

[Real Robot Challenge @robo_challenge]

Tired of Atari? Try to run RL on real-robots and participate in the https://t.co/Djo586AZjj, an official NeurIPS21 challenge. Submit your jobs to the robot like to a cluster and extend any of the baselines for winning prizes! Starting now!

[Francesco Locatello @FrancescoLocat8]

Towards Causal Representation Learning: led by @bschoelkopf and myself, with amazing co-authors Stefan Bauer, @rosemary_ke, @NalKalchbrenner, @anirudhg9119, Yoshua Bengio, accepted in the Proceedings of the IEEE.

Link: https://t.co/CENDcC2GRd

[Tom Howard 🦎 @TomHowardFilm]

HAD to be done
#BostonDynamics
#FlightOfTheConchords

[Prakash Haridas @prakashph]

Yup, this is pretty much the situation so far. #Elections2020 https://t.co/EGeKje78HM

[Animesh Garg @animesh_garg]

Isaac Gym - @NVIDIAAI physics simulation environment for reinforcement learning research (preview Release)
- End-to-End GPU accelerated
- Isaac Gym tensor-based APIs fo massively parallel sim
https://t.co/O6icJ13qH1

Also get in touch for potential internships to flex in Gym!

[Sam Mady @sam_s_mady]

Thanks @IEEESpectrum for the cover on CausalWorld

https://t.co/SKNfulJ7Vo

[Andrea Dittadi @andrea_dittadi]

New paper: On the Transfer of Disentangled Representations in Realistic Settings. We scale up disentangled representations to a new high-resolution robotics dataset and investigate the role of disentanglement in Out-Of-Distribution generalization.

https://t.co/jpZN9UZ5Wr [1/4]

[Reuters @Reuters]

Researchers in Switzerland have given ANYmal - their four legged-robot - wheels, making it even faster on all terrains

[Judea Pearl @yudapearl]

Fascinating new paper on incorporating causal thinking in robotic actions.

[ETH Zurich @ETH_en]

The newly founded ETH AI Center unites reasearchers of #AI across all departments. Join the official inauguration virtually on October 20th from 16.00 to 18.00 CET. Further information and registration: https://t.co/NHp7b3kupt @CSatETH

[ETH CS Department @CSatETH]

We are excited about the opening of the #ETH AI Center, which virtually opens its doors on October 20. Register here to be part of the official inauguration: https://t.co/zfjlxca5Yy

https://t.co/4rFiWWsxOR

[Sam Mady @sam_s_mady]

https://t.co/Sus5v8sHpz work done w/ Frederik Träuble*, @anirudhg9119 , Alexander Neitz, @manuelwuethrich, Yoshua Bengio, @bschoelkopf, Stefan Bauer (9/9)

[Sam Mady @sam_s_mady]

CausalWorld is an open-source simulation framework and benchmark for causal structure and transfer learning in a robotic manipulation environment where tasks range from rather simple to extremely hard. Work done at @MPI_IS and @MILAMontreal. (1/9)

https://t.co/86G08g7izy

[Sam Mady @sam_s_mady]

Finally, The environment is a simulation of an open-source robotic platform, hence offering the possibility of sim-to-real transfer, by 3D printing your own robot in the lab. (8/9)