activity
20192022
most citedPlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference

9 citations · 12 across the 3 of their papers we have counts for

collaborators

6 papers

cs.AI20223 cited

Multi-View Dreaming: Multi-View World Model with Contrastive Learning

Akira Kinose, Masashi Okada, Ryo Okumura +1

In this paper, we propose Multi-View Dreaming, a novel reinforcement learning agent for integrated recognition and control from multi-view observations by extending Dreaming. Most…

cs.LG2022

DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction

Masashi Okada, Tadahiro Taniguchi

The present paper proposes a novel reinforcement learning method with world models, DreamingV2, a collaborative extension of DreamerV2 and Dreaming. DreamerV2 is a cutting-edge mod…

cs.LG2020

Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction

Masashi Okada, Tadahiro Taniguchi

In the present paper, we propose a decoder-free extension of Dreamer, a leading model-based reinforcement learning (MBRL) method from pixels. Dreamer is a sample- and cost-efficien…

cs.LG20209 cited

PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference

Masashi Okada, Norio Kosaka, Tadahiro Taniguchi

In the present paper, we propose an extension of the Deep Planning Network (PlaNet), also referred to as PlaNet of the Bayesians (PlaNet-Bayes). There has been a growing demand in…

cs.CV2019

Multi-person Pose Tracking using Sequential Monte Carlo with Probabilistic Neural Pose Predictor

Masashi Okada, Shinji Takenaka, Tadahiro Taniguchi

It is an effective strategy for the multi-person pose tracking task in videos to employ prediction and pose matching in a frame-by-frame manner. For this type of approach, uncertai…

cs.LG2019

Variational Inference MPC for Bayesian Model-based Reinforcement Learning

Masashi Okada, Tadahiro Taniguchi

In recent studies on model-based reinforcement learning (MBRL), incorporating uncertainty in forward dynamics is a state-of-the-art strategy to enhance learning performance, making…