Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.
arXiv preprint arXiv:2101.07123 , year=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
SVL reframes goal-conditioned RL as a survival analysis problem, expressing the value function as a discounted sum of survival probabilities trained via maximum likelihood.
Frames online zero-shot transfer with BFMs as a bandit problem and derives an eigenvalue-minimization exploration strategy under linear reward approximation.
Text2BFM aligns language with a frozen BFM via a text-aligned variational behavioral bottleneck to generate long motions by decoding latents into policy actions.
Universal horizon models extend geometric horizon models to arbitrary horizons and apply winsorized distributions for stable offline RL value learning, outperforming baselines on 100 OGBench tasks.
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.
Robust minimax task inference in BFMs achieves dynamics-shift robustness from nominal offline data alone and outperforms standard baselines.
BYOL-γ uses self-predictive representations to approximate successor representations, improving zero-shot combinatorial generalization in goal-conditioned behavioral cloning.
InFOM applies flow matching to model intention-conditioned occupancy measures for RL pre-training, reporting 1.8x median return gains and 36% higher success rates on benchmarks.
Temporal abstraction functions as a low-pass filter on transition dynamics to lower the effective rank of successor representations while bounding value function error in forward-backward learning.
citing papers explorer
-
Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning
Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.
-
SVL: Goal-Conditioned Reinforcement Learning as Survival Learning
SVL reframes goal-conditioned RL as a survival analysis problem, expressing the value function as a discounted sum of survival probabilities trained via maximum likelihood.
-
Exploration and Online Transfer with Behavioral Foundation Models
Frames online zero-shot transfer with BFMs as a bandit problem and derives an eigenvalue-minimization exploration strategy under linear reward approximation.
-
Plan, Don't Pose: Long Composite Motion Generation with Text-Aligned BFM
Text2BFM aligns language with a frozen BFM via a text-aligned variational behavioral bottleneck to generate long motions by decoding latents into policy actions.
-
Offline Reinforcement Learning with Universal Horizon Models
Universal horizon models extend geometric horizon models to arbitrary horizons and apply winsorized distributions for stable offline RL value learning, outperforming baselines on 100 OGBench tasks.
-
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
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.
-
When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited
Robust minimax task inference in BFMs achieves dynamics-shift robustness from nominal offline data alone and outperforms standard baselines.
-
Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning
BYOL-γ uses self-predictive representations to approximate successor representations, improving zero-shot combinatorial generalization in goal-conditioned behavioral cloning.
-
Intention-Conditioned Flow Occupancy Models
InFOM applies flow matching to model intention-conditioned occupancy measures for RL pre-training, reporting 1.8x median return gains and 36% higher success rates on benchmarks.
-
Spectral Alignment in Forward-Backward Representations via Temporal Abstraction
Temporal abstraction functions as a low-pass filter on transition dynamics to lower the effective rank of successor representations while bounding value function error in forward-backward learning.
- Towards Human Motion World Models via Executable Behaviour Representations