Hindsight Generative Adversarial Imitation Learning
This addresses the challenge of data acquisition in imitation learning for AI agents, though it appears incremental as it builds on existing frameworks.
The paper tackles the problem of imitation learning requiring costly expert demonstrations by proposing Hindsight Generative Adversarial Imitation Learning (HGAIL), which achieves comparable performance to existing methods without needing demonstrations.
Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, which poses a significant challenge in some scenarios. A promising alternative is to train agent learning skills via imitation learning without expert demonstrations, which, to some extent, would extremely expand imitation learning areas. To achieve such expectation, in this paper, we propose Hindsight Generative Adversarial Imitation Learning (HGAIL) algorithm, with the aim of achieving imitation learning satisfying no need of demonstrations. Combining hindsight idea with the generative adversarial imitation learning (GAIL) framework, we realize implementing imitation learning successfully in cases of expert demonstration data are not available. Experiments show that the proposed method can train policies showing comparable performance to current imitation learning methods. Further more, HGAIL essentially endows curriculum learning mechanism which is critical for learning policies.