Zorlu5454/ppo-scratch-LunarLander-v2

PPO Agent Playing LunarLander-v2

PPO implemented from scratch (CleanRL style) for Unit 8 of the Deep RL Course.

Hyperparameters

env_id: LunarLander-v2
seed: 1
total_timesteps: 1000000
learning_rate: 0.0003
num_envs: 16
num_steps: 256
anneal_lr: True
gamma: 0.999
gae_lambda: 0.98
num_minibatches: 32
update_epochs: 4
norm_adv: True
clip_coef: 0.2
clip_vloss: True
ent_coef: 0.01
vf_coef: 0.5
max_grad_norm: 0.5
batch_size: 4096
minibatch_size: 128
num_updates: 244