DEFlow: Deep Equilibrium Flow for Maximum-Entropy Reinforcement Learning
Overview
DEFlow improves policy sampling with implicit integration, achieving 10% better coverage in docking tasks and top returns in manipulation. It balances diversity and precision with extra computational cost, supporting implicit flow policies in reinforcement learning.
Generated from attributed reports · Updated 2 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · manipulation tasks: 5 other · Basis not reported
“n time-averaged return on four of five manipulation tasks, while remaining broadly competitive across five MuJoCo tasks. These results support implicit flow policies for tasks requiring both diversity and precision, at the cost of additional nonlinear and linear solves. Primary”
Exact source · revision 3Source owner not reported
Reported quantity · MuJoCo tasks: 5 other · Basis not reported
“n time-averaged return on four of five manipulation tasks, while remaining broadly competitive across five MuJoCo tasks. These results support implicit flow policies for tasks requiring both diversity and precision, at the cost of additional nonlinear and linear solves. Primary”
Exact source · revision 3Source owner not reported
Reported quantity · Multi-Goal docking variants: 4 other · Basis not reported
“ystem. We combine implicit differentiation with a discrete change-of-variables formula for the final-action density, enabling off-policy training within soft actor-critic without backpropagating through solver iterations. DEFlow achieves an average relative improvement of approximately 10% in mean successful coverage over the strongest baseline across four Multi-Goal docking variants. It also achieves the highest mea”
Exact source · revision 3Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsDEFlow: Deep Equilibrium Flow for Maximum-Entropy Reinforcement Learning
DEFlow improves policy sampling with implicit integration, achieving 10% better coverage in docking tasks and top returns in manipulation. It balances diversity and precision with extra computational cost.
- arXiv Robotics — research abstractsLearning Robust Visuomotor Policies via Dynamics Alignment
This research proposes DAP, a policy framework that couples action generation with an action-conditioned dynamics model to improve robustness in visuomotor tasks. By co-sampling actions and future observations through flow extrapolation, DAP achieves the highest average success rate across four simulated and three real-world tasks, with relative improvements of 56.5% in simulation and 33.3% in the real world over the strongest baseline. The method also recovers self-consistent action-future pairs when future-observation estimates are corrupted.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).