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
+- Swimmer-v4
 model-index:
 - name: TRPO
   results:

agent.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da72c217c90ed70cdf5d48e9ff03ca7e09cb1e93eb57c10a1f3bcc769e304b98
-size 24230
+oid sha256:7651691ef61f40961b15c60bc3da78b6bb93fa696719dd7d686b530d3afe6ed4
+size 25354