Off-policy RL entry scores 0.990 RDS on CoRL 2026 RoboEval
A π0.5 policy trained with AWR, RECAP, generated demos and failure recoveries also scores 0.987 on official seeds.
Stories per day · 30 days
Relatedrobotics5reinforcement-learning4libero3simulation2agents1assembly1benchmark1bimanual1coda1embodied-ai1long-form-video1manipulation1nist1onewm1robocasa1roboteval1video-generation1vision-language1
10 stories, newest first · one card per story
Stories tagged #policy-learning
WeVisCut trains a 9B agent for narration-to-video editing
Trained on more than 130,000 examples, the 9B policy matches Claude Opus 5 while using nearly 33 times fewer tokens.
CoDA: Co-Evolution of Data Engines and Action Policies
CoDA co-evolves robot simulation data and policies, lifting out-of-distribution success from 5.3% to 27.6%.
Can World and Action Modeling Benefit Each Other under Unified Causal Training?
OneWM shows unified causal training lets world modeling and action learning improve each other.
CoDA: Co-Evolution of Data Engines and Action Policies
CoDA co-evolves simulation data engines and robot policies, lifting out-of-distribution manipulation success.
AlphaNIST
Researchers train one robot policy to complete all twenty NIST assembly-board tasks using success-guided sampling.
LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC
LeWAM is a decoder-free JEPA world action model that predicts dynamics and policies while planning in policy-head noise space.
Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition
Claude Opus 5.5 with Claude Code won six of twelve AAArena adversarial game ladders.
Agent Priors-guided Policy Learning
APPL uses each skill policy's structural prior so robots compose skills and generalize from few demonstrations.
Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport
OptiFlow learns one-step multimodal flow policies for offline RL via state-wise entropic optimal transport, avoiding critic overestimation and mode collapse.