DeepMimic: Example-Guided Deep RL of Physics-Based Character Skills
April 14, 2018, 7:55 a.m.
By:
Kirti Bakshi
A goal in character animation that has been longstanding is the combination of a data-driven specification of behaviour with ...
Dopamine - Research framework for fast prototyping of reinforcement learning algorithms.
Sept. 7, 2018, 8:58 a.m.
By:
Kirti Bakshi
Over the past few years, Reinforcement learning (RL) research has seen a number of significant advances and the ...
Holodeck - High Fidelity Simulator for Reinforcement Learning and Robotics Research.
Oct. 15, 2018, 12:46 p.m.
By:
Kirti Bakshi
Here you are presented to the release the first public version of a high-fidelity simulator that has been built ...