Add `agent.pt` and tag the environment

This commit adds a model that is compatible with the 🥇 [Open RL Leaderboard](https://huggingface.co/spaces/open-rl-leaderboard/leaderboard) 🥇.

README.md

@@ -5,6 +5,7 @@ tags:
 - deep-reinforcement-learning
 - reinforcement-learning
 - stable-baselines3
+- Humanoid-v4
 model-index:
 - name: TRPO
   results:

agent.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25401e0dcca211204da0159d75033762afb96db836eef0624915e6eba58ac107
-size 122406
+oid sha256:74762ae6ab75a4b1c4eca607a0bb2add4df05f26076ecf0d7f28eab69ca1d472
+size 129418