The authors trained hierarchical agents in four one-on-one games: Ant Sumo, Ant Fencing, Franka Air Hockey and G1 Boxing.
Competitive self-play discovers compact motor skills humans can directly control
A hierarchical agent learned discrete, interpretable behaviors that people could combine to complete unseen control tasks without retraining.
Big Tech
Seungeun Rho · Jeonghwan Kim · Xue Bin Peng · Sehoon Ha
Georgia Institute of Technology · Simon Fraser University · NVIDIA
Research Digest··3 min read
Rho et al.
Why this paper
From NVIDIA and 2 others
In one line
Competitive self-play yields a small set of motor skills that humans can directly compose to solve new tasks without retraining.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§