Humanoid

The 'Humanoid' dataset/benchmark contains a set of challenging reinforcement learning tasks designed to evaluate the performance of algorithms in simulating humanoid movements and behaviors.

Papers using Humanoid (5)

D2 Actor Critic: Diffusion Actor Meets Distributional Critic2025An Advantage-based Optimization Method for Reinforcement Learning in Large Action Space2024 · 1 citesText-Aware Diffusion for Policy Learning2024Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning2024From Goal-Conditioned to Language-Conditioned Agents via Vision-Language Models2024