Discriminator Soft Actor Critic without Extrinsic Rewards
arXiv:2001.06808
Abstract
It is difficult to be able to imitate well in unknown states from a small amount of expert data and sampling data. Supervised learning methods such as Behavioral Cloning do not require sampling data, but usually suffer from distribution shift. The methods based on reinforcement learning, such as inverse reinforcement learning and generative adversarial imitation learning (GAIL), can learn from only a few expert data. However, they often need to interact with the environment. Soft Q imitation learning addressed the problems, and it was shown that it could learn efficiently by combining Behavioral Cloning and soft Q-learning with constant rewards. In order to make this algorithm more robust to distribution shift, we propose Discriminator Soft Actor Critic (DSAC). It uses a reward function based on adversarial inverse reinforcement learning instead of constant rewards. We evaluated it on PyBullet environments with only four expert trajectories.
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- Addressing Function Approximation Error in Actor-Critic Methods
- Soft Actor-Critic Algorithms and Applications
- Generative Adversarial Imitation Learning
- A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
- ChainerRL: A Deep Reinforcement Learning Library
- SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards
- Reinforcement Learning for Robotic Manipulation using Simulated Locomotion Demonstrations