chore: import upstream snapshot with attribution

2026-07-13 13:17:40 +08:00
commit f1825c8ceb
10096 changed files with 2364182 additions and 0 deletions
@@ -0,0 +1,35 @@
+# @OldAPIStack
+# Pendulum SAC can attain -150+ reward in 6-7k
+# Configurations are the similar to original softlearning/sac codebase
+pendulum-sac:
+    env: Pendulum-v1
+    run: SAC
+    stop:
+        env_runners/episode_return_mean: -250
+        timesteps_total: 10000
+    config:
+        # Works for both torch and tf.
+        framework: torch
+        q_model_config:
+          fcnet_activation: relu
+          fcnet_hiddens: [256, 256]
+        policy_model_config:
+          fcnet_activation: relu
+          fcnet_hiddens: [256, 256]
+        tau: 0.005
+        target_entropy: auto
+        n_step: 1
+        rollout_fragment_length: 1
+        train_batch_size: 256
+        target_network_update_freq: 1
+        min_sample_timesteps_per_iteration: 1000
+        replay_buffer_config:
+          type: MultiAgentPrioritizedReplayBuffer
+        num_steps_sampled_before_learning_starts: 256
+        optimization:
+          actor_learning_rate: 0.0003
+          critic_learning_rate: 0.0003
+          entropy_learning_rate: 0.0003
+        num_env_runners: 0
+        num_gpus: 0
+        metrics_num_episodes_for_smoothing: 5