Fetching the paper…

Reading the bibliography…

2023

Learning Video-Conditioned Policies for Unseen Manipulation Tasks

Chane-Sane, Elliot, Schmid, Cordelia, Laptev, Ivan

Original
PDF
Post on X

Understand

The ability to specify robot commands by a non-expert user is critical for building generalist agents capable of solving a large variety of tasks.

One convenient way to specify the intended robot goal is by a video of a person demonstrating the target task.
While prior work typically aims to imitate human demonstrations performed in robot environments, here we focus on a more realistic and challenging setup with demonstrations recorded in natural and diverse human environments.
We propose Video-conditioned Policy learning (ViP), a data-driven approach that maps human demonstrations of previously unseen tasks to robot manipulation skills.

Learning Video-Conditioned Policies for Unseen Manipulation Tasks · Around

Built on

R. Goyal, S. Ebrahimi Kahou, V. Michalski, J. Materzynska, S. Westphal, H. Kim, V. Haenel, I. Fruend, P. Yianilos, M. Mueller-Freitag
2017
Earlier work this paper cites.
M. Babaeizadeh, C. Finn, D. Erhan, R. H. Campbell, and S. Levine, “Stochastic variational video prediction,”
Original
2017
Earlier work this paper cites.
R. S. Sutton and A. G. Barto,
2018
Earlier work this paper cites.
A. V. Nair, V. Pong, M. Dalal, S. Bahl, S. Lin, and S. Levine, “Visual reinforcement learning with imagined goals,”
2018
Earlier work this paper cites.
V. Pong, S. Gu, M. Dalal, and S. Levine, “Temporal difference models: Model-free deep rl for model-based control,”
Original
2018
Earlier work this paper cites.
D. Damen, H. Doughty, G. M. Farinella, S. Fidler, A. Furnari, E. Kazakos, D. Moltisanti, J. Munro, T. Perrett, W. Price
2018
Earlier work this paper cites.
X. B. Peng, A. Kanazawa, J. Malik, P. Abbeel, and S. Levine, “Sfv: Reinforcement learning of physical skills from videos,”
2018
Earlier work this paper cites.
Y. Liu, A. Gupta, P. Abbeel, and S. Levine, “Imitation from observation: Learning to imitate behaviors from raw video via context translation,” in
2018
Earlier work this paper cites.
P. Sermanet, C. Lynch, Y. Chebotar, J. Hsu, E. Jang, S. Schaal, S. Levine, and G. Brain, “Time-contrastive networks: Self-supervised learning from video,” in
2018
Earlier work this paper cites.
T. Yu, C. Finn, A. Xie, S. Dasari, T. Zhang, P. Abbeel, and S. Levine, “One-shot imitation from observing humans via domain-adaptive meta-learning,”
Original
2018
Earlier work this paper cites.
D. Ghosh, A. Gupta, A. Reddy, J. Fu, C. Devin, B. Eysenbach, and S. Levine, “Learning to reach goals via iterated supervised learning,”
Original
2019
Earlier work this paper cites.
A. Gupta, V. Kumar, C. Lynch, S. Levine, and K. Hausman, “Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning,”
Original
2019
Earlier work this paper cites.
A. Miech, D. Zhukov, J.-B. Alayrac, M. Tapaswi, I. Laptev, and J. Sivic, “Howto100m: Learning a text-video embedding by watching hundred million narrated video clips,” in
2019
Earlier work this paper cites.
P. Sharma, D. Pathak, and A. Gupta, “Third-person visual imitation learning via decoupled hierarchical controller,”
2019
Earlier work this paper cites.
L. Smith, N. Dhawan, M. Zhang, P. Abbeel, and S. Levine, “Avid: Learning multi-stage tasks via pixel-level translation of human videos,”
Original
2019
Earlier work this paper cites.
S. Pirk, M. Khansari, Y. Bai, C. Lynch, and P. Sermanet, “Online object representations with contrastive learning,”
Original
2019
Earlier work this paper cites.
A. D. Edwards and C. L. Isbell, “Perceptual values from observation,”
Original
2019
Earlier work this paper cites.
A. Kumar, X. B. Peng, and S. Levine, “Reward-conditioned policies,”
Original
2019
Earlier work this paper cites.

Similar

J. Schmidhuber, “Reinforcement learning upside down: Don’t predict rewards–just map them to actions,”
Original
2019
Cited alongside, same era.
R. K. Srivastava, P. Shyam, F. Mutz, W. Jaśkowski, and J. Schmidhuber, “Training agents using upside-down reinforcement learning,”
Original
2019
Cited alongside, same era.
Y. Ding, C. Florensa, P. Abbeel, and M. Phielipp, “Goal-conditioned imitation learning,”
2019
Cited alongside, same era.
C. Lynch, M. Khansari, T. Xiao, V. Kumar, J. Tompson, S. Levine, and P. Sermanet, “Learning latent plans from play,” in
2020
Cited alongside, same era.
B. Eysenbach, R. Salakhutdinov, and S. Levine, “C-learning: Learning to achieve goals via recursive classification,”
Original
2020

Then

A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark
2021
Later among the works it cites.
S. Emmons, B. Eysenbach, I. Kostrikov, and S. Levine, “Rvs: What is essential for offline rl via supervised learning?”
Original
2021
Later among the works it cites.
H. Furuta, Y. Matsuo, and S. S. Gu, “Generalized decision transformer for offline hindsight information matching,”
Original
2021
Later among the works it cites.
L. Chen, K. Lu, A. Rajeswaran, K. Lee, A. Grover, M. Laskin, P. Abbeel, A. Srinivas, and I. Mordatch, “Decision transformer: Reinforcement learning via sequence modeling,”
2021
Later among the works it cites.
M. Janner, Q. Li, and S. Levine, “Offline reinforcement learning as one big sequence modeling problem,”
2021

Beyond the bibliography

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

Open on alphaXiv

alphaXiv is searching for related work…

Cited alongside, same era.

C. Lynch and P. Sermanet, “Language conditioned imitation learning over unstructured data,”

2020

Cited alongside, same era.

P. Khosla, P. Teterwak, C. Wang, A. Sarna, Y. Tian, P. Isola, A. Maschinot, C. Liu, and D. Krishnan, “Supervised contrastive learning,”

2020

Cited alongside, same era.

N. Das, S. Bechtle, T. Davchev, D. Jayaraman, A. Rai, and F. Meier, “Model-based inverse reinforcement learning from visual demonstrations,”

2020

Cited alongside, same era.

V. Petrík, M. Tapaswi, I. Laptev, and J. Sivic, “Learning object manipulation skills via approximate state estimation from real videos,”

2020

Cited alongside, same era.

A. Bonardi, S. James, and A. J. Davison, “Learning one-shot imitation from humans without humans,”

2020

Cited alongside, same era.

K. Schmeckpeper, O. Rybkin, K. Daniilidis, S. Levine, and C. Finn, “Reinforcement learning with videos: Combining offline observations with interaction,”

2020

Cited alongside, same era.

K. Schmeckpeper, A. Xie, O. Rybkin, S. Tian, K. Daniilidis, S. Levine, and C. Finn, “Learning predictive models from observation and interaction,” in

2020

Cited alongside, same era.

Later among the works it cites.

M. Ahn, A. Brohan, N. Brown, Y. Chebotar, O. Cortes, B. David, C. Finn, K. Gopalakrishnan, K. Hausman, A. Herzog

2022

Later among the works it cites.

E. Jang, A. Irpan, M. Khansari, D. Kappler, F. Ebert, C. Lynch, S. Levine, and C. Finn, “Bc-z: Zero-shot task generalization with robotic imitation learning,” in

2022

Later among the works it cites.

Y. Lu, K. Hausman, Y. Chebotar, M. Yan, E. Jang, A. Herzog, T. Xiao, A. Irpan, M. Khansari, D. Kalashnikov

2022

Later among the works it cites.

S. Nair, E. Mitchell, K. Chen, S. Savarese, C. Finn

2022

Later among the works it cites.

O. Mees, L. Hermann, and W. Burgard, “What matters in language conditioned robotic imitation learning,”

2022

Later among the works it cites.

O. Mees, L. Hermann, E. Rosete-Beas, and W. Burgard, “Calvin: A benchmark for language-conditioned policy learning for long-horizon robot manipulation tasks,”

2022

Later among the works it cites.

K. Grauman, A. Westbury, E. Byrne, Z. Chavis, A. Furnari, R. Girdhar, J. Hamburger, H. Jiang, M. Liu, X. Liu

2022

Later among the works it cites.

S. Bahl, A. Gupta, and D. Pathak, “Human-to-robot imitation in the wild,”

2022

Later among the works it cites.

S. Nair, A. Rajeswaran, V. Kumar, C. Finn, and A. Gupta, “R3m: A universal visual representation for robot manipulation,”

2022

Later among the works it cites.

T. Xiao, I. Radosavovic, T. Darrell, and J. Malik, “Masked visual pre-training for motor control,”

2022

Later among the works it cites.

Y. Seo, K. Lee, S. L. James, and P. Abbeel, “Reinforcement learning with action-free pre-training from videos,” in

2022

Later among the works it cites.

M. Shridhar, L. Manuelli, and D. Fox, “Cliport: What and where pathways for robotic manipulation,” in

2022

Later among the works it cites.

L. Fan, G. Wang, Y. Jiang, A. Mandlekar, Y. Yang, H. Zhu, A. Tang, D.-A. Huang, Y. Zhu, and A. Anandkumar, “Minedojo: Building open-ended embodied agents with internet-scale knowledge,”

2022

Later among the works it cites.