Rousslan Dossa

Rousslan Dossa

Deep Reinforcement Learning Researcher at Araya Inc. Aspiring to create a universal intelligent agents that will teach me back and maybe turn me into such an agent myself.

A Human-Like Agent Based on a Hybrid of Reinforcement and Imitation Learning

Rousslan Fernand Julien Dossa, Xinyu Lian, Hirokazu Nomoto, Takashi Matsubara, Kuniaki Uehara

Full text and PDF available in Proceedings of 2019 International Joint Conference on Neural Networks (IJCNN).

Backup

Share on

Twitter Facebook LinkedIn

Leave a comment

You may also enjoy

Soft Actor-Critic: Re-Implementation and Experiments

An attempt at expanding upon the theory and motivation behind the Soft Actor-Critic algorithm for continuous and discrete action space, as well as their resp...

Masked Autoencoder for Distribution Estimation (MADE) Implementation and Experiments

Diving into the autoregressive models for unsupervised reinforcement learning with a focus on the MADE algorithm. Aims a exposing the theory in an intuitive ...

Deep Deterministic Policy Gradient

Going over the theory and implementation of the DDPG method. Also provides some benchmark on a handful of environments, and the effect of some specific imple...

Exploration schemes in Deep Q-Networks (DQN)

Investigating the impact of various exploration schemes on the DQN performance and learning efficiency.