Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learningby Andreas Schlaginhaufen, Maryam KamgarpourFirst…
MOSEAC: Streamlined Variable Time Step Reinforcement Learningby Dong Wang, Giovanni BeltrameFirst submitted to arxiv on:…
A New View on Planning in Online Reinforcement Learningby Kevin Roice, Parham Mohammad Panahi, Scott…
Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyondby Xutong Liu, Siwei…
CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Frameworkby Yiyang Zhao, Yunzhuo Liu, Bo Jiang, Tian…
The Importance of Online Data: Understanding Preference Fine-tuning via Coverageby Yuda Song, Gokul Swamy, Aarti…
Learning to Play Atari in a World of Tokensby Pranav Agarwal, Sheldon Andrews, Samira Ebrahimi…
A Fast Convergence Theory for Offline Decision Makingby Chenjie Mao, Qiaosheng ZhangFirst submitted to arxiv…
Deep reinforcement learning for weakly coupled MDP’s with continuous actionsby Francisco Robledo, Urtzi Ayesta, Konstantin…
Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignmentby Chen Zhang, Qiang…