naoto yoshida

gym_torcs. C++

DQN-chainer. Python

RL_nyu-mon. MATLAB

mujoco_marker_example. examples of mujoco-py marker

nonpara_discrete_rl. Simple Nonparametric Reinforcement Learning with Universal Interface

two_resource_environment. DQN agent in 3D two resource problem for foraging task

openended_homeostatic_rl. Unexpected Capability of Homeostatic Reinforcement Learning for Open-ended Skill Acquisition

deeprl_gfn. Deep homeostatic reinforcement learning to explain long-term nutritional strategies

gather_env. Gather Environment for RL Benchmarking

ste. Sample code of straight-through gradient estimator of stochastic neural networks

pydata_okinawa2017. Jupyter Notebook

conv_ae. Convolutional Autoencoders Examples

mcmc_demo. Python

random_agent_for_LIS. This is the random agent for LIS. This agent doesn't load and use caffe pre-trained model, and keeps taking random actions.

hrl_bs_ijcnn2023. Python

homeostatic_crafter. Python

tiny_transformer_samples. tiny Transformer examples

moving_copy_in_chainer. Python

backprop_doc.

fisher_ratio. calculating fisher discrimination ratio

template_unity_mlagents_env. This is a template unity setting of the mlagents for deep model training

CarND-Capstone. Udacity Self-driving car Engineer Program Final Project

daw_twostep. Reprecation of Daw's two-step task simulation

loss_landscape. Plotting the landscape of loss function of the auto encoder using random vectors