add EpisodeAwareSampler (#217)

Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
这个提交包含在:
Radek Osmulski
2024-05-31 22:43:47 +10:00
提交者 GitHub
父节点 83f4f7f7e8
当前提交 504d2aaf48
共有 4 个文件被更改,包括 168 次插入 和 1 次删除

查看文件

@ -44,6 +44,10 @@ training:
observation.state: "[i / ${fps} for i in range(1 - ${policy.n_obs_steps}, 1)]"
action: "[i / ${fps} for i in range(1 - ${policy.n_obs_steps}, 1 - ${policy.n_obs_steps} + ${policy.horizon})]"
# The original implementation doesn't sample frames for the last 7 steps,
# which avoids excessive padding and leads to improved training results.
drop_n_last_frames: 7 # ${policy.horizon} - ${policy.n_action_steps} - ${policy.n_obs_steps} + 1
eval:
n_episodes: 50
batch_size: 50