Update readme with blog post link (#5452)

README.md

@@ -4,7 +4,7 @@
 
 ## Overview
 
-The [ML-Agents](https://github.com/Unity-Technologies/ml-agents) DodgeBall environment is a third-person cooperative shooter where players try to pick up as many balls as they can, then throw them at their opponents. It comprises two game modes: Elimination and Capture the Flag. In Elimination, each group tries to eliminate all members of the other group by hitting them with balls. In Capture the Flag, players try to steal the other team’s flag and bring it back to their base. In both modes, players can hold up to four balls, and dash to dodge incoming balls and go through hedges. You can find more information about the environment at the corresponding blog post.
+The [ML-Agents](https://github.com/Unity-Technologies/ml-agents) DodgeBall environment is a third-person cooperative shooter where players try to pick up as many balls as they can, then throw them at their opponents. It comprises two game modes: Elimination and Capture the Flag. In Elimination, each group tries to eliminate all members of the other group by hitting them with balls. In Capture the Flag, players try to steal the other team’s flag and bring it back to their base. In both modes, players can hold up to four balls, and dash to dodge incoming balls and go through hedges. You can find more information about the environment at the corresponding [blog post](https://blog.unity.com/technology/ml-agents-plays-dodgeball).
 
 This environment is intended to be used with the new features announced in [ML-Agents 2.0](https://blog.unity.com/technology/ml-agents-v20-release-now-supports-training-complex-cooperative-behaviors), namely cooperative behaviors and variable length observations. By using the [MA-POCA trainer](https://github.com/Unity-Technologies/ml-agents/blob/release_18_docs/docs/Learning-Environment-Design-Agents.md#groups-for-cooperative-scenarios), [variable length observations](https://github.com/Unity-Technologies/ml-agents/blob/release_18_docs/docs/Learning-Environment-Design-Agents.md#groups-for-cooperative-scenarios), and [self-play](https://github.com/Unity-Technologies/ml-agents/blob/release_18_docs/docs/Learning-Environment-Design-Agents.md#teams-for-adversarial-scenarios), you can train teams of DodgeBall agents to play against each other. Trained agents are also provided in this project to play with, as both your allies and your opponents.