ICRA 2026PastReinforcement learning
ICRA 2026 Workshop on Reinforcement Learning in the Era of Imitation Learning
ICRA 2026 Workshop RL4IL
- Submission deadline
- Mar 21, 2026, 18:00 UTCOpenReview-synced 2026-03-21 18:00 UTC (as of 2026-06-23) — extensions on OpenReview are applied automatically; verify on the website.
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (24)
Fetched from OpenReview (v2) on 2026-06-10.
Behavior Cloning of MPC for 3-DOF Robotic Manipulators
Beyond Imitation: Reinforcement Learning–Based Sim–Real Co-Training for VLA Models
Can Agents Learn Safe Behavior From Non-Preferred Demonstrations?
Climb with SHERPA: Heuristic-Guided Reinforcement Learning via Segmented Experience Relay
Coherent Off-Policy Improvement of Large Behaviour Models with Learned Rewards
Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation
Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation
Graph-Based Reward Learning and Automatic Subtask Discovery for Long-Horizon Manipulation
Hi-CoLA: High Confidence Lower Bound Approximation Based Reinforcement Learning for Flex-Route Transit Operation Control
Imitation from Videos: Monocular 3D Motion Estimation for Agile Quadruped Locomotion
KhGRL: Kernelized human-Guided Reinforcement Learning
Mini Diffuser: Accelerating Diffusion Policy Optimization via Two-Level Minibatching
Negative Energy as Reward: Optimizing Beyond Demonstrations in Offline Goal-Conditioned Control
Online Fine-Tuning of Pretrained Controllers for Autonomous Driving via Real-Time Recurrent RL
Online Planning with Offline Pretrained All-in-One World Model
ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning
Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows
Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
Teacher-Student Representational Alignment for Reinforcement Learning-driven Imitation Learning
Tune to Learn: How Controller Gains Shape Robot Policy Learning
Turning the Dial: Bridging Behavior Cloning and Reinforcement Learning via Timestep Modulation
Vision-Language-Action Jump-Starting for Reinforcement Learning Robotic Agents
When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning