PokeRL trains PPO agents to finish early Pokemon Red tasks using a loop-aware environment wrapper, multi-layer anti-loop mechanisms, and dense hierarchical rewards.
The pokeagent challenge: Competitive and long-context learning at scale
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
PokeRL: Reinforcement Learning for Pokemon Red
PokeRL trains PPO agents to finish early Pokemon Red tasks using a loop-aware environment wrapper, multi-layer anti-loop mechanisms, and dense hierarchical rewards.
- ASH: Agents that Self-Hone via Embodied Learning