The Risks of Invariant Risk Minimization
https://arxiv.org/abs/2010.05761
https://arxiv.org/abs/2010.05761
Forwarded from Just links
CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning https://openreview.net/forum?id=SK7A5pdrgov
OpenReview
CausalWorld: A Robotic Manipulation Benchmark for Causal Structure...
Despite recent successes of reinforcement learning (RL), it remains a challenge for agents to transfer learned skills to related environments. To facilitate research addressing this problem, we...
A comparative study of counterfactual estimators
https://arxiv.org/abs/1704.00773
https://arxiv.org/abs/1704.00773
Learning Invariant Representations for Reinforcement Learning without Reconstruction
https://arxiv.org/abs/2006.10742
https://arxiv.org/abs/2006.10742
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
https://openreview.net/forum?id=ryxWIgBFPS
https://openreview.net/forum?id=ryxWIgBFPS
OpenReview
A Meta-Transfer Objective for Learning to Disentangle Causal...
This paper proposes a meta-learning objective based on speed of adaptation to transfer distributions to discover a modular decomposition and causal variables.
Invariant Causal Prediction for Block MDPs
https://arxiv.org/abs/2003.06016
https://arxiv.org/abs/2003.06016