Takuya Hiraoka (TakuyaHiraoka)

TakuyaHiraoka

Geek Repo

Location:Tokyo-3, Japan

Home Page:https://takuyahiraoka.github.io

Github PK Tool:Github PK Tool

Takuya Hiraoka's repositories

Dropout-Q-Functions-for-Doubly-Efficient-Reinforcement-Learning

Source files to replicate experiments in my ICLR 2022 paper.

Efficient-SRGC-RL-with-a-High-RR-and-Regularization

Source files to replicate experiments in my Arxiv 2023 paper.

Language:PythonLicense:MITStargazers:1Issues:0Issues:0

Soft-Actor-Critic-and-Extensions

PyTorch implementation of Soft-Actor-Critic and Prioritized Experience Replay (PER) + Emphasizing Recent Experience (ERE) + Munchausen RL + D2RL and parallel Environments.

Language:PythonLicense:MITStargazers:1Issues:0Issues:0

Which-Experiences-Are-Influential-for-RL-Agents

Source files to replicate experiments in my ArXiv 2024 paper.

Language:PythonLicense:MITStargazers:1Issues:0Issues:0

d3rlpy

An offline deep reinforcement learning library

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

d4rl

A benchmark for offline reinforcement learning.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

deep_bisim4control

Learning Invariant Representations for Reinforcement Learning without Reconstruction

License:NOASSERTIONStargazers:0Issues:0Issues:0
License:NOASSERTIONStargazers:0Issues:0Issues:0

dm_control

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

ElegantRL

Scalable and Elastic Deep Reinforcement Learning Using PyTorch. Please star. 🔥

License:NOASSERTIONStargazers:0Issues:0Issues:0
License:MITStargazers:0Issues:0Issues:0

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

License:MITStargazers:0Issues:0Issues:0

mbrl-lib

Library for Model Based RL

License:MITStargazers:0Issues:0Issues:0

Meta-Model-Based-Meta-Policy-Optimization

Source files to replicate experiments in my ACML 2021 paper.

Stargazers:0Issues:0Issues:0

metaworld

An open source robotics benchmark for meta- and multi-task reinforcement learning

License:MITStargazers:0Issues:0Issues:0

mopo

Code for MOPO: Model-based Offline Policy Optimization

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

mujoco

Multi-Joint dynamics with Contact. A general purpose physics simulator.

License:Apache-2.0Stargazers:0Issues:0Issues:0

mujoco-maze

Simple maze environments using mujoco-py

License:Apache-2.0Stargazers:0Issues:0Issues:0

oyster

Implementation of Efficient Off-policy Meta-learning via Probabilistic Context Variables (PEARL)

License:MITStargazers:0Issues:0Issues:0

pianoplayer

Automatic fingering generator for piano scores

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

pomdp-baselines

Simple (but often Strong) Baselines for POMDPs in PyTorch - ICML 2022

License:MITStargazers:0Issues:0Issues:0

ray

An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.

License:Apache-2.0Stargazers:0Issues:0Issues:0

REDQ

Author's PyTorch implementation of Randomized Ensembled Double Q-Learning (REDQ) algorithm.

License:MITStargazers:0Issues:0Issues:0

rltorch

A simple framework for distributed reinforcement learning in PyTorch.

License:MITStargazers:0Issues:0Issues:0

robopianist

🎹 🤖 A benchmark for high-dimensional robot control.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0

soft-actor-critic.pytorch

A PyTorch implementation of Soft Actor-Critic(SAC).

License:MITStargazers:0Issues:0Issues:0
Stargazers:0Issues:0Issues:0
Language:HTMLStargazers:0Issues:2Issues:0

ToolBench

An open platform for training, serving, and evaluating large language model for tool learning.

License:Apache-2.0Stargazers:0Issues:0Issues:0