Reinforcement Learning

Training agents to make decisions? Benchmark your policies on game playing, continuous control, and offline learning tasks.

3 tasks2 datasets9 results

Tasks & Benchmarks

Atari Games

Playing Atari video games (Atari 2600 benchmark).

1 datasets9 resultsSOTA tracked

Continuous Control

Control tasks with continuous action spaces (MuJoCo).

1 datasets0 results

Offline RL

Learning from fixed datasets without environment interaction.

0 datasets0 results
Show all datasets and SOTA results

Atari Games

Atari 2600Arcade Learning Environment (Atari 2600)2013
SOTA:40000(human-normalized-score)
Go-Explore

Suite of 57 Atari 2600 games. Standard benchmark for deep reinforcement learning agents.

Continuous Control

MuJoCoMulti-Joint dynamics with Contact2012

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

Offline RL

No datasets indexed yet. Contribute on GitHub
Reinforcement Learning Benchmarks - CodeSOTA | CodeSOTA