GCRL and MISL are unified as control maximization, with three inequivalent GCRL formulations each matched to a MISL objective via bounds on goal-sensitivity.
CIC: Contrastive intrinsic control for unsupervised skill discovery
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
GS-HER generalizes hindsight relabeling to query-defined goal sets, enabling inference-time goal predicates for offline goal-conditioned RL while improving performance on tasks bottlenecked by nuisance state dimensions.
MASEM samples constrained manifolds with unknown disconnected components via entropy-maximizing k-NN resampling, achieving exponential mean-field KL reduction and order-of-magnitude Sinkhorn improvement on benchmarks.
pcsp is a shared RL policy using LLM persona embeddings, low-rank projection, and PPO+InfoNCE+KL training that delivers 17x above-chance zero-shot persona identification and 22x faster inference on a 300-persona benchmark.
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
citing papers explorer
-
Manifold Sampling via Entropy Maximization
MASEM samples constrained manifolds with unknown disconnected components via entropy-maximizing k-NN resampling, achieving exponential mean-field KL reduction and order-of-magnitude Sinkhorn improvement on benchmarks.