Files
2026-07-13 13:17:40 +08:00

23 lines
597 B
YAML

# @OldAPIStack
cartpole-sac:
env: CartPole-v1
run: SAC
stop:
env_runners/episode_return_mean: 150.0
timesteps_total: 100000
config:
# Works for both torch and tf.
framework: torch
gamma: 0.95
target_network_update_freq: 32
tau: 1.0
# initial_alpha: 0.5
train_batch_size: 32
optimization:
actor_learning_rate: 0.005
critic_learning_rate: 0.005
entropy_learning_rate: 0.0001
# grad_norm_clipping: 40.0
# evaluation_config:
# explore: true