Discriminator Soft Actor Critic Without Extrinsic Rewards

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.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keynishio2020discriminator

Related papers

• Extrinsicaly Rewarded Soft Q Imitation Learning With Discriminator (2024)0.00
• Iq-learn: Inverse Soft-q Learning For Imitation (2021)0.00
• Discriminator-actor-critic: Addressing Sample Inefficiency And Reward Bias In Adversarial Imitation Learning (2018)0.00
• Self-supervised Adversarial Imitation Learning (2023)0.00
• Distributional Soft Actor-critic With Diffusion Policy (2025)0.00
• Learning From Demonstrations With SACR2: Soft Actor-critic With Reward Relabeling (2021)0.00
• Regularized Soft Actor-critic For Behavior Transfer Learning (2022)3.58
• Distributional Soft Actor-critic: Off-policy Reinforcement Learning For Addressing Value Estimation Errors (2020)17.77