Deep Learning and Robotics

AI with Objectives/Goals n Robotics n Marketing / Advertising n Dialogue n Optimizing operations / logistics n Queue management ...

From Pixels to Actions? Pong Enduro Beamrider Q*bert Pieter Abbeel --UC Berkeley | Gradescope| Covariant.AI ...

[Source: Mnihet al., Nature 2015 (DeepMind) ] Deep Q-Network (DQN): From Pixels to Joystick Commands 32 8x8 filters with stride ...

[ Source: Mnihet al., Nature 2015 (DeepMind) ] Pieter Abbeel --UC Berkeley | Gradescope| Covariant.AI ...

Deep RL Success Stories DQNMnihet al, NIPS 2013 / Nature 2015 MCTSGuoet al, NIPS 2014; TRPOSchulman, Levine, Moritz, Jordan, Abb ...

Deep RL Success Stories AlphaGoSilver et al, Nature 2015 AlphaGoZeroSilver et al, Nature 2017 Tian et al, 2016; Maddison et al, ...

n Super-human agent on a competitive game, enabled by n Reinforcement learning n Self-play n Enough computation n Cooperation em ...

Learning Locomotion [Schulman, Moritz, Levine, Jordan, Abbeel, ICLR 2016] Pieter Abbeel --UC Berkeley | Gradescope| Covariant.AI ...

Deep RL: Learn to Pass/Protect [Bansal et al, 2017] Pieter Abbeel --UC Berkeley | Gradescope| Covariant.AI ...

Deep RL: Learn Soccer [Bansal et al, 2017] Pieter Abbeel --UC Berkeley | Gradescope| Covariant.AI ...

Deep RL: Virtual Stuntman [Peng, Abbeel, Levine, van de Panne, 2018] Pieter Abbeel --UC Berkeley | Gradescope| Covariant.AI ...

Deep RL: Dynamic Animation for Motion Picture [Peng, Abbeel, Levine, van de Panne, 2018] Pieter Abbeel --UC Berkeley | Gradescop ...

BRETT: Berkeley Robot for the Elimination of Tedious Tasks [Levine, Finn, Darrell, Abbeel, JMLR 2016] Pieter Abbeel --UC Berkele ...

Unsupervised Learning for Interaction? [Levine et al, 2016] Pieter Abbeel --UC Berkeley | Gradescope| Covariant.AI ...

Application: Google Datacenter Cooling 40% reduction in cooling cost https://deepmind.com/blog/deepmind-ai-reduces-google-data-c ...

Deep Reinforcement Learning -- NASA SUPERball [Geng, Zhang, Bruce*, Caluwaerts, Vespignani, Sunspiral, Abbeel, Levine, ICRA 2017 ...

How About a Hand? [OpenAIRobotics Team] Pieter Abbeel --UC Berkeley | Gradescope| Covariant.AI ...

Speed Up Deep RL through Imitation Pieter Abbeel --UC Berkeley | Gradescope| Covariant.AI ...

Human Demonstrations [Zhang, McCarthy, Jow, Lee, Chen, Goldberg, Abbeel, ICRA 2018] Pieter Abbeel --UC Berkeley | Gradescope| Co ...

n Deep learning successes n Supervised learning = pattern recognition, if enough data (input -> output pairs), then neural ne ...