diff --git a/configs/ppo/dev_larger_timesteps_larger_rolloutsteps.yaml b/configs/ppo/dev_larger_timesteps_larger_rolloutsteps.yaml new file mode 100644 index 0000000..b2f629a --- /dev/null +++ b/configs/ppo/dev_larger_timesteps_larger_rolloutsteps.yaml @@ -0,0 +1,16 @@ +learning_rate: 0.0003 +total_timesteps: 1228800 +num_envs: 32 +num_steps: 64 +anneal_lr: true +gamma: 0.99 +gae_lambda: 0.95 +num_minibatches: 32 +update_epochs: 4 +norm_adv: true +clip_coef: 0.2 +clip_vloss: true +ent_coef: 0.005 +vf_coef: 1.0 +max_grad_norm: 0.5 +target_kl: null \ No newline at end of file