Anastasiia Pedan
@pedanana.bsky.social
thank you, Claas, you're the best mentor I could've asked for!!!!
June 20, 2025 at 5:05 PM
thank you, Claas, you're the best mentor I could've asked for!!!!
This was an amazing collaboration with a cracked team consisting of @cvoelcker.bsky.social, me, Arash Ahmadian, Romina Abachi, @igilitschenski.bsky.social, and @sologen.bsky.social
#ReinforcementLearning #ModelBasedRL #RLTheory #ICML2025
#ReinforcementLearning #ModelBasedRL #RLTheory #ICML2025
June 19, 2025 at 2:40 AM
This was an amazing collaboration with a cracked team consisting of @cvoelcker.bsky.social, me, Arash Ahmadian, Romina Abachi, @igilitschenski.bsky.social, and @sologen.bsky.social
#ReinforcementLearning #ModelBasedRL #RLTheory #ICML2025
#ReinforcementLearning #ModelBasedRL #RLTheory #ICML2025
For more details, feel free to come chat with us in Vancouver⛰️🌲🌊 and check out our paper🤖! www.arxiv.org/abs/2505.22772
Calibrated Value-Aware Model Learning with Probabilistic Environment Models
The idea of value-aware model learning, that models should produce accurate value estimates, has gained prominence in model-based reinforcement learning. The MuZero loss, which penalizes a model's val...
www.arxiv.org
June 19, 2025 at 2:40 AM
For more details, feel free to come chat with us in Vancouver⛰️🌲🌊 and check out our paper🤖! www.arxiv.org/abs/2505.22772
We can correct the MuZero loss and other losses from the same family by pushing the value estimates computed from different sampled model rollouts to have the correct variance and mean. We prove the soundness of this change and show that it is beneficial for agent performance 📈📈📈!
June 19, 2025 at 2:40 AM
We can correct the MuZero loss and other losses from the same family by pushing the value estimates computed from different sampled model rollouts to have the correct variance and mean. We prove the soundness of this change and show that it is beneficial for agent performance 📈📈📈!
Getting a correct value estimate is instrumental in model-based RL, so if your algorithm fails to provide correct targets for model learning, your agent is in trouble because these errors will accumulate fast 📉📉📉!
June 19, 2025 at 2:40 AM
Getting a correct value estimate is instrumental in model-based RL, so if your algorithm fails to provide correct targets for model learning, your agent is in trouble because these errors will accumulate fast 📉📉📉!