Finally we show that it is possible to interleave the motion capture tracking with training on complementary tasks, enriching the resulting skill space, and enabling the reuse of skills not well covered by the motion capture data such as getting up from the ground or catching a ball.
Along with this model, we also provide a set of reinforcement learning tasks, including reference motion tracking, running, and neck control, used to infer muscle actuation patterns.
Deep reinforcement learning has been one of the fastest growing fields of machine learning over the past years and numerous libraries have been open sourced to support research.
Being able to reach any desired location in the environment can be a valuable asset for an agent.
Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty.
This approach achieves a linear increase of the number of network outputs with the number of degrees of freedom by allowing a level of independence for each individual action dimension.