[KongchangAI]
Benchmark

Pendulum

A classic control task in reinforcement learning: a continuous inverted pendulum control system that requires a finely timed control policy to keep the pole upright.

Timeline (last 90 days)

Oct 14

The five classic control tasks usually refer to CartPole, Acrobot, MountainCar, Pendulum, etc., whose common feature is that the state changes continuously, the reward is per-step or approximately sparse, and the required precision of policy timing is far higher than LLM generation.

Unverified50%

All Facts (1)

Unverified

The five classic control tasks usually refer to CartPole, Acrobot, MountainCar, Pendulum, etc., whose common feature is that the state changes continuously, the reward is per-step or approximately sparse, and the required precision of policy timing is far higher than LLM generation.

50%

Source Articles

Why GRPO Can Train Reasoning LLMs But Can't Teach a Robot to WalkOct 14