Reinforced Imitation Learning by Free Energy Principle

no code implementations • 25 Jul 2021 • Ryoya Ogishima, Izumi Karino, Yasuo Kuniyoshi

Reinforcement Learning (RL) requires a large amount of exploration especially in sparse-reward settings.

Imitation Learning Reinforcement Learning (RL)

Combining Imitation and Reinforcement Learning with Free Energy Principle

no code implementations • 1 Jan 2021 • Ryoya Ogishima, Izumi Karino, Yasuo Kuniyoshi

Imitation Learning (IL) and Reinforcement Learning (RL) from high dimensional sensory inputs are often introduced as separate problems, but a more realistic problem setting is how to merge the techniques so that the agent can reduce exploration costs by partially imitating experts at the same time it maximizes its return.

Imitation Learning reinforcement-learning +1

Identifying Critical States by the Action-Based Variance of Expected Return

no code implementations • 26 Aug 2020 • Izumi Karino, Yoshiyuki Ohmura, Yasuo Kuniyoshi

Our results also demonstrate that the identified critical states are intuitively interpretable regarding the crucial nature of the action selection.

Reinforcement Learning (RL)

Switching Isotropic and Directional Exploration with Parameter Space Noise in Deep Reinforcement Learning

no code implementations • 18 Sep 2018 • Izumi Karino, Kazutoshi Tanaka, Ryuma Niiyama, Yasuo Kuniyoshi

Moreover, this method switches isotropic exploration and directional exploration in parameter space with regard to obtained rewards.

OpenAI Gym reinforcement-learning +1