A reward model is a learned function that scores how well an agent's behavior accomplishes a task, either as a single number per episode or as a per-frame signal. It replaces a hand-engineered reward where one is impractical to write: "is the towel folded?" is easy to judge and hard to code. The modern template comes from Christiano et al., "Deep Reinforcement Learning from Human Preferences" (2017), which learned a reward model from human comparisons of trajectory segments and optimized a policy against it, solving tasks "without access to the reward function".
In robot learning, reward models serve three roles: the reward signal for real-world reinforcement learning, a success detector that ends episodes, and a score for weighting or filtering demonstration data. LeRobot v0.6.1 includes several. HIL-SERL trains a vision-based reward classifier from a handful of demonstrations. SARM is a video-based, stage-aware reward model for long-horizon manipulation, usable with Reward-Aligned Behavior Cloning. Robometer predicts "dense, frame-level task progress and frame-level success from a trajectory video and a task description". TOPReward is a zero-shot reward model that reads token log-probabilities from an off-the-shelf VLM.
These models appear in this matrix but are not robot policies: they never command actuators, so they are listed outside the compatibility grid and have no robot cells.
A common misconception is that a reward model is ground truth. A policy optimized against a learned reward can exploit its errors, so success rates scored by the same model used for training overstate real performance. Independent evaluation, by people or by scripted checks, is still required.