Reinforcement Learning

Continuous Control

Control tasks with continuous action spaces (MuJoCo).

1 datasets0 results

Continuous Control is a key task in reinforcement learning. Below you will find the standard benchmarks used to evaluate models, along with current state-of-the-art results.

Benchmarks & SOTA

MuJoCo

Multi-Joint dynamics with Contact

20120 results

Physics engine for continuous control tasks like walking, running, and manipulation.

No results tracked yet

Related Tasks

Atari Games

Playing Atari video games (Atari 2600 benchmark).

Offline RL

Learning from fixed datasets without environment interaction.

Back to Reinforcement Learning

Continuous Control Benchmarks - Reinforcement Learning - CodeSOTA | CodeSOTA