mirror of
https://github.com/vale981/ray
synced 2025-03-06 02:21:39 -05:00
19 lines
554 B
YAML
19 lines
554 B
YAML
# This configuration can expect to reach -160 reward in 10k-20k timesteps
|
|
pendulum-td3:
|
|
env: Pendulum-v1
|
|
run: TD3
|
|
stop:
|
|
episode_reward_mean: -900
|
|
timesteps_total: 100000
|
|
config:
|
|
# Works for both torch and tf.
|
|
framework: tf
|
|
# === Model ===
|
|
actor_hiddens: [64, 64]
|
|
critic_hiddens: [64, 64]
|
|
# === Exploration ===
|
|
replay_buffer_config:
|
|
type: MultiAgentReplayBuffer
|
|
learning_starts: 5000
|
|
exploration_config:
|
|
random_timesteps: 5000
|