MSPR: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning
cs.LG
Submitted: 2026-05-10
Updated: 2026-10-06
Terminology
Sources
- Deep Variational Information Bottleneck
- Revisiting Feature Prediction for Learning Visual Representations from Video
- Scalable methods for computing state similarity in deterministic Markov Decision Processes
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- DeepMDP: Learning Continuous Latent Space Models for Representation Learning
- World Models
- Learning Latent Dynamics for Planning from Pixels
- Dream to Control: Learning Behaviors by Latent Imagination
- Mastering Diverse Domains through World Models
- TD-MPC2: Scalable, Robust World Models for Continuous Control
- Gaussian Error Linear Units (GELUs)
- Offline Reinforcement Learning with Implicit Q-Learning
- Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning
- Goal-Conditioned Reinforcement Learning: Problems and Solutions
- Decoupled Weight Decay Regularization
- Learning Latent Plans from Play
- VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
- Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following
- OGBench: Benchmarking Offline Goal-Conditioned RL
- Is Value Learning Really the Main Bottleneck in Offline RL?
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks