https://openreview.net/forum?id=JmKAYb7I00
Revisiting Energy Based Models as Policies: Ranking Noise Contrastive Estimation and Interpolating...
A crucial design decision for any robot learning pipeline is the choice of policy representation: what type of model should be used to generate the next set of...
energy based models
https://arxiv.org/abs/2106.07832
[2106.07832] Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient...
Abstract page for arXiv paper 2106.07832: Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent
energy based modelslearning
https://research.nvidia.com/publication/2023-05_bayesian-reparameterization-reward-conditioned-reinforcement-learning-energy
Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models |...
Recently, reward-conditioned reinforcement learning (RCRL) has gained popularity due to its simplicity, flexibility, and off-policy nature. However, we will...
reinforcement learningenergy basedbayesianrewardconditioned