Semi-supervised reward learning for offline reinforcement learning

by   Ksenia Konyushkova, et al.

In offline reinforcement learning (RL) agents are trained using a logged dataset. It appears to be the most natural route to attack real-life applications because in domains such as healthcare and robotics interactions with the environment are either expensive or unethical. Training agents usually requires reward functions, but unfortunately, rewards are seldom available in practice and their engineering is challenging and laborious. To overcome this, we investigate reward learning under the constraint of minimizing human reward annotations. We consider two types of supervision: timestep annotations and demonstrations. We propose semi-supervised learning algorithms that learn from limited annotations and incorporate unlabelled data. In our experiments with a simulated robotic arm, we greatly improve upon behavioural cloning and closely approach the performance achieved with ground truth rewards. We further investigate the relationship between the quality of the reward model and the final policies. We notice, for example, that the reward models do not need to be perfect to result in useful policies.


Offline Learning from Demonstrations and Unlabeled Experience

Behavior cloning (BC) is often practical for robot learning because it a...

Online Semi-Supervised Learning in Contextual Bandits with Episodic Reward

We considered a novel practical problem of online learning with episodic...

Reinforcement Learning with a Corrupted Reward Channel

No real-world reward function is perfect. Sensory errors and software bu...

XIRL: Cross-embodiment Inverse Reinforcement Learning

We investigate the visual cross-embodiment imitation setting, in which a...

How to Leverage Unlabeled Data in Offline Reinforcement Learning

Offline reinforcement learning (RL) can learn control policies from stat...

Semi-Supervised Dialogue Policy Learning via Stochastic Reward Estimation

Dialogue policy optimization often obtains feedback until task completio...

Reinforcement Learning with Perturbed Rewards

Recent studies have shown the vulnerability of reinforcement learning (R...