LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

The University of Tokyo

Soichiro Nishimori

PhD student. Interested in Game AI, JAX-based RL, offline RL and exploration.

GitHub @nissymori1 Website

Followers

38

Public repos

17

Stars (recent)

257

Ecosystems

1

Projects

Repositories this builder owns.

nissymori.github.io

No description.

3

The Official JAX Code for "Retry Policy Gradients for Continuous Action Spaces"

3

[ICML2026] Official JAX code for Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying

8

Clean single-file implementation of offline RL algorithms in JAX

Connected narratives

AI Agents Consumer Crypto SocialFi Stablecoins Agent Commerce Onchain Apps

Related builders

Others building in the same ecosystem.

[RLC2025] Official code for "Offline Reinforcement Learning with Domain-Unlabeled Data"

[TMLR2026] Official code for "On Symmetric Losses for Policy Optimization with Noisy Preferences"

A GPU-Accelerated Mahjong Simulator for RL in JAX

remin_offline_rl

No description.

Recent activity

Most recently pushed work.

nissymori/nissymori.github.io
pushed 16d ago
nissymori/ReMAC
pushed 16d ago
nissymori/remax-rl
pushed 16d ago
nissymori/JAX-CORL
pushed 16d ago