jtoy / sensenet
SenseNet is a sensorimotor and touch simulator for deep reinforcement learning research
☆57Updated last year
Related projects ⓘ
Alternatives and complementary repositories for sensenet
- Neural Task Programming☆81Updated 6 years ago
- Some hard problems for reinforcement learning.☆32Updated 6 years ago
- Our NIPS 2017: Learning to Run source code☆56Updated last year
- Augmented RNN memory via live SGD☆39Updated 7 years ago
- Models built with TensorFlow☆25Updated 5 years ago
- [ICML-18] Codes for the custom games we built to compare RL agents with humans☆67Updated 6 years ago
- [NeurIPS 2019] Code for the paper "Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity"☆112Updated 4 years ago
- Learning to walk with genetic algorithms by optimizing a truncated Fourier series, applied to a realistic bio-mechanical model of the hum…☆36Updated 7 years ago
- General Game Playing with Schema Networks☆41Updated 2 years ago
- 3d cartpole gym env using bullet physics trained from pixels with tensorflow LRPG, DDPG & NAF☆58Updated 7 years ago
- A parallel version of Trust Region Policy Optimization☆65Updated 7 years ago
- Code to reproduce the results in the "Unsupervised Learning of Goal Spaces for Intrinsically Motivated Exploration"☆21Updated 6 years ago
- Dataset for the spaceship task from "Metacontrol for Adaptive Imagination-Based Optimization"☆55Updated 7 years ago
- Tutorial on continuous control at Reinforcement Learning Summer School 2017.☆34Updated 7 years ago
- Rapprentice: software for teaching robots by example☆30Updated 11 years ago
- Code for the paper "Learning to Act by Predicting the Future", Alexey Dosovitskiy and Vladlen Koltun, ICLR 2017☆150Updated 2 months ago
- ☆30Updated 6 years ago
- Code for NeurIPS 2019 paper: "Symmetry-Based Disentangled Representation Learning requires Interaction with Environments" by H. Caselles-…☆35Updated 4 years ago
- ☆24Updated 9 years ago
- Tensorflow Implementation of Programmable Agents☆36Updated 7 years ago
- Reason8.ai PyTorch solution for NIPS RL 2017 challenge☆84Updated 5 years ago
- Reward Learning by Simulating the Past☆43Updated 5 years ago
- [deprecated] Bridge from Gym to ROS robots☆75Updated last year
- TensorFlow A2C to solve Acrobot, with synchronized parallel environments☆35Updated 6 years ago
- Add-on package to gym, to record sequences of actions, observations, and rewards☆71Updated last year
- ☆19Updated 8 years ago
- Training Sonic with RLlib☆57Updated last year
- Reimplementation code for the paper "Generative Temporal Models with Spatial Memory for Partially Observed Environments"☆29Updated 2 years ago
- OpenAI Retro Contest☆65Updated last year