Hopper-v-4

'Hopper-v-4' is a challenging benchmark in reinforcement learning used to evaluate the performance of algorithms, particularly in terms of their ability to adapt and improve exploration strategies.

Papers using Hopper-v-4 (3)

CAMEL: Continuous Action Masking Enabled by Large Language Models for Reinforcement Learning2025 · 1 citesUncertainty-Aware Reward Discounting for Mitigating Reward Hacking2026ARISE: Adaptive Reinforcement Integrated with Swarm Exploration2026