Youtor
DR3 ValueBased Deep RL Requires Explicit Regularization
>> YOUR LINK HERE: ___ http://youtube.com/watch?v=P7bygduR4hc
Paper at: https://arxiv.org/abs/2112.04716. Presented at NeurIPS 2021 Deep Reinforcement Workshop (Contributed talk), ICML 2021 workshop on Overparameterization: Pitfalls and Opportunities (Spotlight), and ICML 2021 workshop on RL for Real Life Workshop (Spotlight). • If you are interested in how implicit bias affects representations in deep Q-learning algorithms, consider checking out our previous work: • Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning • https://openreview.net/forum?id=O9bni... (Aviral Kumar*, Rishabh Agarwal*, Dibya Ghosh, Sergey Levine)
#############################
