Preference-based reinforcement learning (RL) has shown potential for teaching agents to
perform the target tasks without a costly, pre-defined reward function by learning the reward …

Abstract Setting up a well-designed reward function has been challenging for many
reinforcement learning applications. Preference-based reinforcement learning (PbRL) …

Reinforcement learning (RL) requires access to a reward function that incentivizes the right
behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL …

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult,
involving meticulous design of reward functions that are sufficiently informative yet easy …

The current reward learning from human preferences could be used to resolve complex
reinforcement learning (RL) tasks without access to a reward function by defining a single …

Conveying complex objectives to reinforcement learning (RL) agents often requires
meticulous reward engineering. Preference-based RL methods are able to learn a more …

Learning a reward function from human preferences is challenging as it typically requires
having a high-fidelity simulator or using expensive and potentially unsafe actual physical …

Designing reward functions is a longstanding challenge in reinforcement learning (RL); it
requires specialized knowledge or domain data, leading to high costs for development. To …

The complexity of designing reward functions has been a major obstacle to the wide
application of deep reinforcement learning (RL) techniques. Describing an agent's desired …

Preference-based reinforcement learning (PbRL) is an approach that enables RL agents to
learn from preference, which is particularly useful when formulating a reward function is …