NikSkywalker
/

ppo-LunarLander-v2-scratch

Reinforcement Learning

deep-reinforcement-learning

custom-implementation

Eval Results (legacy)

Model card Files Files and versions

PPO Agent for LunarLander-v2 (Unit 8)

This is a trained model of a PPO agent for LunarLander-v2, trained from scratch using PyTorch.

Training Results

The agent achieves a mean reward of 285.12 after 2,000,000 timesteps.

Downloads last month: -; Downloads are not tracked for this model. How to track

Video Preview

Reinforcement Learning

loading

Evaluation results

mean_reward on LunarLander-v2
self-reported

285.12 +/- 20.0