Abrar Anwar
239 posts
@_abraranwar
CS PhD student at @USCViterbi + intern @nvidia | prev intern @Cornell @SandiaLabs | undergrad @UTCompSci
Super excited to share Robometer, a reward model that works zero-shot across robots, tasks, and scenes! Try fine-tuning Robometer on your own dataset! 🌐Project website: robometer.github.io 💻Code: github.com/robometer/robo…
Tested robometer on an oven temperature selection task (ground truth is 200). Results based on temperature referenced in prompt: - 160: highest when rotating dial - 180: highest at start - 200: highest at end really impressive instruction following!
Reward curves look good for maniskill rollouts out of the box! Next up is throwing this in a MPC controller =) Nice work @Jesse_Y_Zhang @aliangdw @_abraranwar @yigitkkorkmaz (+others)
A reward model that works, zero-shot, across robots, tasks, and scenes? Introducing Robometer: Scaling general-purpose robotic reward models with 1M+ trajectories. Enables zero-shot: online/offline/model-based RL, data retrieval + IL, automatic failure detection, and more! 🧵 (1/12)
A reward model that works, zero-shot, across robots, tasks, and scenes? Introducing Robometer: Scaling general-purpose robotic reward models with 1M+ trajectories. Enables zero-shot: online/offline/model-based RL, data retrieval + IL, automatic failure detection, and more! 🧵 (1/12)
Inspired by the TopReward paper, I made a lil web tool to test these robot manipulation rewards on your own videos. Try: philfung.github.io/rewardscope Record yourself folding a towel, upload it, and compare: 1. TopReward (this paper) 2. GVL (Deepmind) 3. Brute Force (i.e. at each frame, ask LLM to reply with a probability) TopReward (Qwen3VL-8B) holds its own surprisingly well against the others, even if those use ChatGPT! Great work @DJiafei, UW, AllenAI, thanks for pushing @VilleKuosmanen.
A reward model that works, zero-shot, across robots, tasks, and scenes? Introducing Robometer: Scaling general-purpose robotic reward models with 1M+ trajectories. Enables zero-shot: online/offline/model-based RL, data retrieval + IL, automatic failure detection, and more! 🧵 (1/12)
A reward model that works, zero-shot, across robots, tasks, and scenes? Introducing Robometer: Scaling general-purpose robotic reward models with 1M+ trajectories. Enables zero-shot: online/offline/model-based RL, data retrieval + IL, automatic failure detection, and more! 🧵 (1/12)
There’s a discussion going on rn about two recent robotic reward models: TOPReward⛰️ and Robometer🌡️ Which one is better? It depends entirely on your objective! Here is a deep dive into the conceptual differences, strengths, and weaknesses of both. 🧵👇
There’s a discussion going on rn about two recent robotic reward models: TOPReward⛰️ and Robometer🌡️ Which one is better? It depends entirely on your objective! Here is a deep dive into the conceptual differences, strengths, and weaknesses of both. 🧵👇
There’s a discussion going on rn about two recent robotic reward models: TOPReward⛰️ and Robometer🌡️ Which one is better? It depends entirely on your objective! Here is a deep dive into the conceptual differences, strengths, and weaknesses of both. 🧵👇
