Aathi07/ppo-LunarLander-v2

PPO Agent Playing LunarLander-v2

This is a from-scratch PyTorch implementation of PPO trained for Unit 8 Part 1 of the Hugging Face Deep RL Course.

Results

Mean reward: 30.00 +/- 52.96 over 10 evaluation episodes.

Usage

Load model.pt into the Agent class defined in the training script and call get_action_and_value on an observation tensor.