electricwapiti
/

ppo-Huggy

Reinforcement Learning

deep-reinforcement-learning

ML-Agents-Huggy

Model card Files Files and versions Metrics Training metrics Community

electricwapiti commited on Aug 16

Commit

ee202c7

•

1 Parent(s): 95ec5a2

Update README.md

Files changed (1) hide show

README.md +6 -1

README.md CHANGED Viewed

@@ -6,7 +6,12 @@ tags:
 - reinforcement-learning
 - ML-Agents-Huggy
 ---
   # **ppo** Agent playing **Huggy**
   This is a trained model of a **ppo** agent playing **Huggy**
   using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).

 - reinforcement-learning
 - ML-Agents-Huggy
 ---
+# **8/15-16/24 : I am curently trying to improve the SpaceInvaders**
+# **DQN algorithm to reach a score above 200 within a limited**
+# **processing time (1 hr GPU, 3 hrs CPU, max 500000 timesteps).**
+# **I am open to hyperparameters/referrals/suggestions! Thanks :)**
+# **Just search for** <i>electricwapiti/dqn-SpaceInvadersNoFrameskip-v4</i>
+<br><br><br><br><br><br><br><br><br><br>
   # **ppo** Agent playing **Huggy**
   This is a trained model of a **ppo** agent playing **Huggy**
   using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).