Search Results - "Voelcker, Claas"

Can we hop in general? A discussion of benchmark selection and design using the Hopper environment by Voelcker, Claas A, Hussing, Marcel, Eaton, Eric

“…Empirical, benchmark-driven testing is a fundamental paradigm in the current RL community. While using off-the-shelf benchmarks in reinforcement learning (RL)…”
Get full text

When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning by Voelcker, Claas, Kastner, Tyler, Gilitschenski, Igor, Farahmand, Amir-massoud

“…We investigate the impact of auxiliary learning tasks such as observation reconstruction and latent self-prediction on the representation learning problem in…”
Get full text

Temporal-Difference Learning Using Distributed Error Signals by Guan, Jonas, Verch, Shon Eduard, Voelcker, Claas, Jackson, Ethan C, Papernot, Nicolas, Cunningham, William A

“…A computational problem in biological reward-based learning is how credit assignment is performed in the nucleus accumbens (NAc). Much research suggests that…”
Get full text

MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL by Voelcker, Claas A, Hussing, Marcel, Eaton, Eric, Farahmand, Amir-massoud, Gilitschenski, Igor

“…Building deep reinforcement learning (RL) agents that find a good policy with few samples has proven notoriously challenging. To achieve sample efficiency,…”
Get full text

Dissecting Deep RL with High Update Ratios: Combatting Value Divergence by Hussing, Marcel, Voelcker, Claas, Gilitschenski, Igor, Farahmand, Amir-massoud, Eaton, Eric

“…We show that deep reinforcement learning algorithms can retain their ability to learn without resetting network parameters in settings where the number of…”
Get full text

Value Gradient weighted Model-Based Reinforcement Learning by Voelcker, Claas, Liao, Victor, Garg, Animesh, Farahmand, Amir-massoud

“…Model-based reinforcement learning (MBRL) is a sample efficient technique to obtain control policies, yet unavoidable modeling errors often lead performance…”
Get full text

lambda$-models: Effective Decision-Aware Reinforcement Learning with Latent Models by Voelcker, Claas A, Ahmadian, Arash, Abachi, Romina, Gilitschenski, Igor, Farahmand, Amir-massoud

“…The idea of decision-aware model learning, that models should be accurate where it matters for decision-making, has gained prominence in model-based…”
Get full text

Structured Object-Aware Physics Prediction for Video Modeling and Planning by Kossen, Jannik, Stelzner, Karl, Hussing, Marcel, Voelcker, Claas, Kersting, Kristian

“…When humans observe a physical system, they can easily locate objects, understand their interactions, and anticipate future behavior, even in settings with…”
Get full text

Queer In AI: A Case Study in Community-Led Participatory AI by QueerInAI, Organizers Of, :, Ovalle, Anaelia, Subramonian, Arjun, Singh, Ashwin, Voelcker, Claas, Sutherland, Danica J, Locatelli, Davide, Breznik, Eva, Klubička, Filip, Yuan, Hang, J, Hetvi, Zhang, Huan, Shriram, Jaidev, Lehman, Kruno, Soldaini, Luca, Sap, Maarten, Deisenroth, Marc Peter, Pacheco, Maria Leonor, Ryskina, Maria, Mundt, Martin, Agarwal, Milind, McLean, Nyx, Xu, Pan, Pranav, A, Korpan, Raj, Ray, Ruchira, Mathew, Sarah, Arora, Sarthak, John, ST, Anand, Tanvi, Agrawal, Vishakha, Agnew, William, Long, Yanan, Wang, Zijie J, Talat, Zeerak, Ghosh, Avijit, Dennler, Nathaniel, Noseworthy, Michael, Jha, Sharvani, Baylor, Emi, Joshi, Aditya, Bilenko, Natalia Y, McNamara, Andrew, Gontijo-Lopes, Raphael, Markham, Alex, Dǒng, Evyn, Kay, Jackie, Saraswat, Manu, Vytla, Nikhil, Stark, Luke

“…2023 ACM Conference on Fairness, Accountability, and Transparency We present Queer in AI as a case study for community-led participatory design in AI. We…”
Get full text