Non-monotone triangular SCMs with mechanism-wise invertibility and context-independent inverse transport are equivalent to exogenous isomorphism and achieve complete counterfactual identifiability, with supporting experiments on synthetic data and MuJoCo tasks.
International Conference on Learning Representations , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.LG 5representative citing papers
TD-MPC2 scales an implicit world-model RL method to a 317M-parameter agent that masters 80 tasks across four domains with a single hyperparameter configuration.
Return-conditional diffusion models for policies outperform offline RL on benchmarks by circumventing dynamic programming and enable constraint or skill composition.
PROWL introduces a KL-constrained adversarial curriculum and prioritized adversarial trajectory buffer to actively discover and correct rare failure modes in action-conditioned video world models.
citing papers explorer
-
Counterfactual identifiability beyond global monotonicity: non-monotone triangular structural causal models
Non-monotone triangular SCMs with mechanism-wise invertibility and context-independent inverse transport are equivalent to exogenous isomorphism and achieve complete counterfactual identifiability, with supporting experiments on synthetic data and MuJoCo tasks.
-
TD-MPC2: Scalable, Robust World Models for Continuous Control
TD-MPC2 scales an implicit world-model RL method to a 317M-parameter agent that masters 80 tasks across four domains with a single hyperparameter configuration.
-
Is Conditional Generative Modeling all you need for Decision-Making?
Return-conditional diffusion models for policies outperform offline RL on benchmarks by circumventing dynamic programming and enable constraint or skill composition.
-
PROWL: Prioritized Regret-Driven Optimization for World Model Learning
PROWL introduces a KL-constrained adversarial curriculum and prioritized adversarial trajectory buffer to actively discover and correct rare failure modes in action-conditioned video world models.
- LASER: Learning Active Sensing for Continuum Field Reconstruction