Update params in humanoid's training

This commit is contained in:
Goncalo Gordo
2024-08-29 14:37:38 +01:00
parent 646455406c
commit ee731506d7
+4 -4
View File
@@ -622,11 +622,11 @@
"outputs": [],
"source": [
"train_fn = functools.partial(\n",
" ppo.train, num_timesteps=30_000_000, num_evals=5, reward_scaling=0.1,\n",
" ppo.train, num_timesteps=20_000_000, num_evals=5, reward_scaling=0.1,\n",
" episode_length=1000, normalize_observations=True, action_repeat=1,\n",
" unroll_length=10, num_minibatches=32, num_updates_per_batch=8,\n",
" discounting=0.97, learning_rate=3e-4, entropy_cost=1e-3, num_envs=2048,\n",
" batch_size=1024, seed=0)\n",
" unroll_length=10, num_minibatches=24, num_updates_per_batch=8,\n",
" discounting=0.97, learning_rate=3e-4, entropy_cost=1e-3, num_envs=3072,\n",
" batch_size=512, seed=0)\n",
"\n",
"\n",
"x_data = []\n",