Meta-Inverse Reinforcement Learning with Probabilistic Context Variables

Abstract

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations, several major challenges remain. First, existing IRL methods learn reward functions from scratch, requiring large numbers of demonstrations to correctly infer the reward for each task the agent may need to perform. Second, existing methods typically assume homogeneous demonstrations for a single behavior or task, while in practice, it might be easier to collect datasets of heterogeneous but related behaviors. To this end, we propose a deep latent variable model that is capable of learning rewards from demonstrations of distinct but related tasks in an unsupervised way. Critically, our model can infer rewards for new, structurally-similar tasks from a single demonstration. Our experiments on multiple continuous control tasks demonstrate the effectiveness of our approach compared to state-of-the-art imitation and inverse reinforcement learning methods.

NeurIPS 2019

Cited by in corpus (11)

• Path Planning using Neural A* Search
• Grounded Relational Inference: Domain Knowledge Driven Explainable Autonomous Driving
• The MAGICAL Benchmark for Robust Imitation
• SIRL: Similarity-based Implicit Representation Learning
• Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation
• Generalized Decision Transformer for Offline Hindsight Information Matching
• Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks
• IQ-Learn: Inverse soft-Q Learning for Imitation
• SQUIRL: Robust and Efficient Learning from Video Demonstration of Long-Horizon Robotic Manipulation Tasks
• HMRL: Hyper-Meta Learning for Sparse Reward Reinforcement Learning Problem
• Off-Dynamics Inverse Reinforcement Learning from Hetero-Domain