ChainerRL: A Deep Reinforcement Learning Library

Fujita, Yasuhiro; Nagarajan, Prabhat; Kataoka, Toshiki; Ishikawa, Takahiro

doi:10.48550/arxiv.1912.03905

Cited by 3 publications

(1 citation statement)

References 12 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using these neural network functions, the PPO target loss function (L t PPO (θ)) was minimized using the Adam optimizer during RL training. PyTorch 24 and PFRL 25 were used for the deep learning and RL frameworks, respectively, for the experiments.…”

Section: Pgmentioning

confidence: 99%

Molecular Design Method Using a Reversible Tree Representation of Chemical Compounds and Deep Reinforcement Learning

Ishitani

Kataoka

Rikimaru

2022

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

Automatic design of molecules with specific chemical and biochemical properties is an important process in material informatics and computational drug discovery. In this study, we designed a novel coarse-grained tree representation of molecules (Reversible Junction Tree; “RJT”) for the aforementioned purposes, which is reversely convertible to the original molecule without external information. By leveraging this representation, we further formulated the molecular design and optimization problem as a tree-structure construction using deep reinforcement learning (“RJT-RL”). In this method, all of the intermediate and final states of reinforcement learning are convertible to valid molecules, which could efficiently guide the optimization process in simple benchmark tasks. We further examined the multiobjective optimization and fine-tuning of the reinforcement learning models using RJT-RL, demonstrating the applicability of our method to more realistic tasks in drug discovery.

show abstract

Section: Pgmentioning

confidence: 99%

Molecular Design Method Using a Reversible Tree Representation of Chemical Compounds and Deep Reinforcement Learning

Ishitani

Kataoka

Rikimaru

2022

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

show abstract

Discriminator Soft Actor Critic without Extrinsic Rewards

Nishio¹,

Kuyoshi²,

Tsuneda³

et al. 2020

Preprint

View full text Add to dashboard Cite

It is difficult to be able to imitate well in unknown states from a small amount of expert data and sampling data. Supervised learning methods such as Behavioral Cloning do not require sampling data, but usually suffer from distribution shift. 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. However, they often need to interact with the environment. Soft Q imitation learning addressed the problems, and it was shown that it could learn efficiently by combining Behavioral Cloning and soft Q-learning with constant rewards. In order to make this algorithm more robust to distribution shift, we propose Discriminator Soft Actor Critic (DSAC). It uses a reward function based on adversarial inverse reinforcement learning instead of constant rewards. We evaluated it on PyBullet environments with only four expert trajectories.

show abstract

Distributed Reinforcement Learning of Targeted Grasping with Active Vision for Mobile Manipulators

Fujita

Uenishi

Ummadisingu

et al. 2020

Preprint

View full text Add to dashboard Cite

Developing personal robots that can perform a diverse range of manipulation tasks in unstructured environments necessitates solving several challenges for robotic grasping systems. We take a step towards this broader goal by presenting the first RL-based system, to our knowledge, for a mobile manipulator that can (a) achieve targeted grasping generalizing to unseen target objects, (b) learn complex grasping strategies for cluttered scenes with occluded objects, and (c) perform active vision through its movable wrist camera to better locate objects. The system is informed of the desired target object in the form of a single, arbitrary-pose RGB image of that object, enabling the system to generalize to unseen objects without retraining. To achieve such a system, we combine several advances in deep reinforcement learning and present a large-scale distributed training system using synchronous SGD that seamlessly scales to multi-node, multi-GPU infrastructure to make rapid prototyping easier. We train and evaluate our system in a simulated environment, identify key components for improving performance, analyze its behaviors, and transfer to a real-world setup.

show abstract

ChainerRL: A Deep Reinforcement Learning Library

Cited by 3 publications

References 12 publications

Molecular Design Method Using a Reversible Tree Representation of Chemical Compounds and Deep Reinforcement Learning

Molecular Design Method Using a Reversible Tree Representation of Chemical Compounds and Deep Reinforcement Learning

Discriminator Soft Actor Critic without Extrinsic Rewards

Distributed Reinforcement Learning of Targeted Grasping with Active Vision for Mobile Manipulators

Contact Info

Product

Resources

About