mirror of
https://github.com/vale981/ray
synced 2025-03-06 10:31:39 -05:00
83e06cd30a
* WIP. * WIP. * WIP. * WIP. * WIP. * Fix * WIP. * Add TD3 quick Pendulum regresison. * Cleanup. * Fix. * LINT. * Fix. * Sort quick_learning test cases, add TD3. * Sort quick_learning test cases, add TD3. * Revert test_checkpoint_restore.py (debugging) changes. * Fix old soft_q settings in documentation and test configs. * More doc fixes. * Fix test case. * Fix test case. * Lower test load. * WIP.
20 lines
527 B
YAML
20 lines
527 B
YAML
# This configuration can expect to reach -160 reward in 10k-20k timesteps
|
|
pendulum-ddpg:
|
|
env: Pendulum-v0
|
|
run: TD3
|
|
stop:
|
|
episode_reward_mean: -130
|
|
time_total_s: 900 # 10 minutes
|
|
config:
|
|
# === Model ===
|
|
actor_hiddens: [64, 64]
|
|
critic_hiddens: [64, 64]
|
|
|
|
# === Exploration ===
|
|
learning_starts: 5000
|
|
exploration_config:
|
|
random_timesteps: 5000
|
|
|
|
# === Evaluation ===
|
|
evaluation_interval: 1
|
|
evaluation_num_episodes: 5
|