Sleeping Robots uses frozen critics and actor snapshots as compact memories to define surrogate objectives combined via Nash bargaining for offline consolidation of shared robot policies in sequential skill learning.
Multi-task learning as a bargaining game
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
APT augments multi-task learning by adapting advanced optimizers via momentum balancing and light direction preservation, delivering performance gains on four standard MTL datasets.
A separate regulator module adaptively scales actions in RL to reduce constraint violations while preserving exploration, yielding up to 126x fewer violations and over 10x higher returns on Safety Gym tasks.
Rosetta proposes a composable multimodal pretraining method with MAOP to prevent catastrophic forgetting when expanding modalities beyond standard MoE and MoT approaches.
citing papers explorer
-
When Robots Sleep: Offline Skill Consolidation for Shared-Policy Robot Learning
Sleeping Robots uses frozen critics and actor snapshots as compact memories to define surrogate objectives combined via Nash bargaining for offline consolidation of shared robot policies in sequential skill learning.
-
Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
-
Delve into the Applicability of Advanced Optimizers for Multi-Task Learning
APT augments multi-task learning by adapting advanced optimizers via momentum balancing and light direction preservation, delivering performance gains on four standard MTL datasets.
-
Constraint-Aware Reinforcement Learning via Adaptive Action Scaling
A separate regulator module adaptively scales actions in RL to reduce constraint violations while preserving exploration, yielding up to 126x fewer violations and over 10x higher returns on Safety Gym tasks.
-
Rosetta: Composable Native Multimodal Pretraining
Rosetta proposes a composable multimodal pretraining method with MAOP to prevent catastrophic forgetting when expanding modalities beyond standard MoE and MoT approaches.
- DanceOPD: On-Policy Generative Field Distillation