diff options
| author | lanchunhui <zch921005@126.com> | 2023-08-10 21:01:52 +0800 |
|---|---|---|
| committer | lanchunhui <zch921005@126.com> | 2023-08-10 21:01:52 +0800 |
| commit | 3f7b11acd5938ca9cbf68646807b0cc84e996f72 (patch) | |
| tree | a2ab6eba84c2455265a978a3af22f3214fb5186b | |
| parent | 186a22521af4c1f56abfaf227d2e85ca03d24c5d (diff) | |
update: notes
| -rw-r--r-- | rl/tutorials/actor_critic.ipynb | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/rl/tutorials/actor_critic.ipynb b/rl/tutorials/actor_critic.ipynb index 1e19940..8ea81dc 100644 --- a/rl/tutorials/actor_critic.ipynb +++ b/rl/tutorials/actor_critic.ipynb @@ -83,6 +83,9 @@ "id": "49ba68fc", "metadata": {}, "source": [ + "- AC\n", + " - Actor: $\\pi(a|s)$\n", + " - Critic: $Q(s, a)$\n", "- Critic\n", " - estimates the value function.\n", " - action-value: $Q$ value\n", |