Timezone: »

Continuous Control with Action Quantization from Demonstrations
Robert Dadashi · Léonard Hussenot · Damien Vincent · Sertan Girgin · Anton Raichuk · Matthieu Geist · Olivier Pietquin

Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #837

In this paper, we propose a novel Reinforcement Learning (RL) framework for problems with continuous action spaces: Action Quantization from Demonstrations (AQuaDem). The proposed approach consists in learning a discretization of continuous action spaces from human demonstrations. This discretization returns a set of plausible actions (in light of the demonstrations) for each input state, thus capturing the priors of the demonstrator and their multimodal behavior. By discretizing the action space, any discrete action deep RL technique can be readily applied to the continuous control problem. Experiments show that the proposed approach outperforms state-of-the-art methods such as SAC in the RL setup, and GAIL in the Imitation Learning setup. We provide a website with interactive videos: https://google-research.github.io/aquadem/ and make the code available: https://github.com/google-research/google-research/tree/master/aquadem.

Author Information

Robert Dadashi (Google Research)
Léonard Hussenot (Google Research, Brain Team)
Damien Vincent (Google Brain)
Sertan Girgin (Google Brain)
Anton Raichuk (Google)
Matthieu Geist (Google)
Olivier Pietquin (GOOGLE BRAIN)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors