Search Results for author:
Found 2 papers, 1 papers with code
Extrinsicaly Rewarded Soft Q Imitation Learning with Discriminator
In order to make this algorithm more robust to distribution shift, we propose more efficient and robust algorithm by adding to this method a reward function based on adversarial inverse reinforcement learning that rewards the agent for performing actions in status similar to the demo.
Discriminator Soft Actor Critic without Extrinsic Rewards
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
