MinAtar

Papers using MinAtar (6)

Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning2026Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions2025Deep Reinforcement Learning with Gradient Eligibility Traces2025Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn2025Ensemble Elastic DQN: A novel multi-step ensemble approach to address overestimation in deep value-based reinforcement learning2025Beyond the Boundaries of Proximal Policy Optimization2024