ugo-nama-kun
Ugoku-Namakemono (Moving Sloth). Computational philosopher. Connectionist. Behavior designer of autonomous robots.
The University of TokyoTokyo, Japan
Pinned Repositories
DQN-chainer
gather_env
Gather Environment for RL Benchmarking
gym_torcs
mujoco_marker_example
examples of mujoco-py marker
nonpara_discrete_rl
Simple Nonparametric Reinforcement Learning with Universal Interface
pydata_okinawa2017
RL_nyu-mon
ste
Sample code of straight-through gradient estimator of stochastic neural networks
two_resource_environment
DQN agent in 3D two resource problem for foraging task
ugo-nama-kun's Repositories
ugo-nama-kun/mujoco_marker_example
examples of mujoco-py marker
ugo-nama-kun/gather_env
Gather Environment for RL Benchmarking
ugo-nama-kun/ste
Sample code of straight-through gradient estimator of stochastic neural networks
ugo-nama-kun/conv_ae
Convolutional Autoencoders Examples
ugo-nama-kun/fisher_ratio
calculating fisher discrimination ratio
ugo-nama-kun/tiny_transformer_samples
tiny Transformer examples
ugo-nama-kun/allostasis_model
allostasis model using homeostatic RL
ugo-nama-kun/cmc_vision
Continuous Motor Control with Vision
ugo-nama-kun/daw_twostep
Reprecation of Daw's two-step task simulation
ugo-nama-kun/deep_q_binary_vector
Matlab code and data used in Deep RL Workshop @ NIPS 2015
ugo-nama-kun/deeprl_gfn
Deep homeostatic reinforcement learning to explain long-term nutritional strategies
ugo-nama-kun/domain_randomization
Example of Domain Randomization
ugo-nama-kun/heatrapy
Python library for simulating heat transfer processes
ugo-nama-kun/hrl_bs_ijcnn2023
ugo-nama-kun/loss_landscape
Plotting the landscape of loss function of the auto encoder using random vectors
ugo-nama-kun/math_model_of_sexual_response
Reproduction of the dynamical system in "Sex, ducks, and rock “n” roll: Mathematical model of sexual response"
ugo-nama-kun/mdp
Markov Decision Process (MDP) Toolbox for Python
ugo-nama-kun/moe
Minimum Openended Environment
ugo-nama-kun/neuralhomeostat_robot
ugo-nama-kun/qibullet
Bullet simulation for SoftBank Robotics robots
ugo-nama-kun/rnn_rl_tmaze
ugo-nama-kun/sandpie_simulation
A simple sandpie simulation
ugo-nama-kun/smoothsoftmax
Smooth 1D/2D Softmax Sample Code
ugo-nama-kun/super_led_chika_chika
ugo-nama-kun/three_legged_ant
An with tree legs
ugo-nama-kun/tiny_empathy
A tiny environment for the emergence of empathic behaviors
ugo-nama-kun/tiny_mhng
Metropolis-Hastings Naming Game
ugo-nama-kun/toy_diffusion
Toy example of Diffusion model
ugo-nama-kun/train_tiny_empathy
ugo-nama-kun/vq-vae
A Minimum Implementation of VQ-VAE