Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations

Aravind Rajeswaran *, Vikash Kumar *, Abhishek Gupta, Giulia Vezzani,

John Schulman, Emanuel Todorov, Sergey Levine

Results

Additional Results

Adroit Hand attempting to reorient the dice. Desired orientation is displayed on the right.

On-going work

WAM arm lending a helping hand to ADROIT hand to help learn some in-hand manipulation skills. (The initial RL rollouts are is quite amusing to observe)

Bibliography

@INPROCEEDINGS{Rajeswaran-RSS-18,
    AUTHOR    = {Aravind Rajeswaran AND Vikash Kumar AND Abhishek Gupta AND
                 Giulia Vezzani AND John Schulman AND Emanuel Todorov AND Sergey Levine},
    TITLE     = "{Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations}",
    BOOKTITLE = {Proceedings of Robotics: Science and Systems (RSS)},
    YEAR      = {2018},
}