31 citations · 144 across the 10 of their papers we have counts for
4 papers · 1 filter
Contrastive Value Learning: Implicit Models for Simple Offline RL
Bogdan Mazoure, Benjamin Eysenbach, Ofir Nachum +1
Model-based reinforcement learning (RL) methods are appealing in the offline setting because they allow an agent to reason about the consequences of actions without interacting wit…
Offline Reinforcement Learning with Fisher Divergence Critic Regularization
Ilya Kostrikov, Jonathan Tompson, Rob Fergus +1
Many modern approaches to offline Reinforcement Learning (RL) utilize behavior regularization, typically augmenting a model-free actor critic algorithm with a penalty measuring div…
Imitation Learning via Off-Policy Distribution Matching
Ilya Kostrikov, Ofir Nachum, Jonathan Tompson
When performing imitation learning from expert demonstrations, distribution matching is a popular approach, in which one alternates between estimating distribution ratios and then…
Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
Ilya Kostrikov, Kumar Krishna Agrawal, Debidatta Dwibedi +2
We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework. The first problem is implicit bias present in the reward functions used…