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.
16 lines
496 B
YAML
16 lines
496 B
YAML
# This can be expected to reach 90 reward within ~1.5-2.5m timesteps / ~150-250 seconds on a K40 GPU
|
|
mountaincarcontinuous-apex-ddpg:
|
|
env: MountainCarContinuous-v0
|
|
run: APEX_DDPG
|
|
stop:
|
|
episode_reward_mean: 90
|
|
config:
|
|
clip_rewards: False
|
|
num_workers: 16
|
|
exploration_config:
|
|
ou_base_scale: 1.0
|
|
n_step: 3
|
|
target_network_update_freq: 50000
|
|
tau: 1.0
|
|
evaluation_interval: 5
|
|
evaluation_num_episodes: 10
|