Towards a Virtual Stuntman

April 12, 2018

Table of Contents

Motion control problems have become standard benchmarks for reinforcement learning, and deep RL methods have been shown to be effective for a diverse suite of tasks ranging from manipulation to locomotion. However, characters trained with deep RL often exhibit unnatural behaviours, bearing artifacts such as jittering, asymmetric gaits, and excessive movement of limbs. Can we train our characters to produce more natural behaviours?

Source: berkeley.edu

Tags :

comments powered by Disqus

Differentiable Plasticity: A New Method Learning to Learn

Neural networks, which underlie many of Uber’s machine learning systems, have proven highly successful in solving complex problems, including image recognition, language understanding, and game-playing. However, these networks are usually trained to a stopping point through gradient descent, which incrementally adjusts the connections of the network based on its performance over many trials. Once the training is complete, the network is fixed and the connections can no longer change; as a result, barring any later re-training (again requiring many examples), the network in effect stops learning at the moment training ends.

Lessons Learned Reproducing a Deep Reinforcement Learning Paper

There are a lot of neat things going on in deep reinforcement learning. One of the coolest things from last year was OpenAI and DeepMind’s work on training an agent using feedback from a human rather than a classical reward signal. There’s a great blog post about it at Learning from Human Preferences, and the original paper is at Deep Reinforcement Learning from Human Preferences.

Towards a Virtual Stuntman

Tags :

Share :

Related Posts

Differentiable Plasticity: A New Method Learning to Learn

Lessons Learned Reproducing a Deep Reinforcement Learning Paper

Spyce Kitchen, a robotic chef built by four recent M.I.T. grads