LunarLander

'LunarLander' is a benchmark used in reinforcement learning that evaluates the performance of algorithms in controlling a spacecraft to land on the lunar surface.

Papers using LunarLander (14)

K-score: Kalman Filter As A Principled Alternative To Reward Normalization In Reinforcement Learning2026Stepscorer: Accelerating Reinforcement Learning With Step-wise Scoring And Psychological Regret Modeling2026Self Paced Gaussian Contextual Reinforcement Learning2026An Approximate Ascent Approach To Prove Convergence of PPO2026A Controlled Study of Double DQN and Dueling DQN Under Cross-Environment Transfer2026TransZero: Parallel Tree Expansion in MuZero using Transformer Networks2025CARoL: Context-aware Adaptation for Robot Learning2025Towards Reinforcement Learning From Neural Feedback: Mapping Fnirs Signals To Agent Performance2025Counterfactual Explanations for Continuous Action Reinforcement Learning2025Learning from Less: SINDy Surrogates in RL2025Towards Reinforcement Learning from Neural Feedback: Mapping fNIRS Signals to Agent Performance2025Proximal Policy Optimization with Evolutionary Mutations2026The Trajectory Alignment Coefficient in Two Acts: From Reward Tuning to Reward Learning2026StepScorer: Accelerating Reinforcement Learning with Step-wise Scoring and Psychological Regret Modeling2026