good_robot

Robotics research project

Research on repurposing reinforcement learning for transfer between tasks in robotics and multi-step visual tasks with simulation-to-real transfer

"Good Robot! Now Watch This!": Repurposing Reinforcement Learning for Task-to-Task Transfer; and “Good Robot!”: Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer

GitHub

108 stars
15 watching
28 forks
Language: Jupyter Notebook
last commit: almost 3 years ago
Linked from 1 awesome list

computer-visiondeep-learningdeep-q-networkdeep-reinforcement-learninggraspinglearning-from-demonstrationmanipulationmulti-step-dqnmulti-step-learningreinforcement-learningrobotic-manipulationroboticssimulationtask-to-task-transfervrep-simulatorzero-shot-learning

Backlinks from these awesome lists:

Related projects:

Repository Description Stars
ahq1993/perceivable-human-robot-interaction-using-neural-attention-q-networks An implementation of a deep reinforcement learning algorithm to teach a robot to interact with humans in a socially acceptable manner. 4
dusty-nv/jetson-reinforcement Provides tools and libraries for training intelligent agents to perform complex tasks in robotics using deep reinforcement learning and GPU acceleration. 891
vita-epfl/crowdnav Develops robot navigation policies in crowded spaces using reinforcement learning and attention mechanisms. 607
humancompatibleai/imitation Provides clean implementations of imitation and reward learning algorithms 1,350
nicrusso7/rex-gym Training an open-source quadruped robot to perform domestic and generic tasks using reinforcement learning and OpenAI Gym. 998
jjakimoto/dqn Reinforcement learning-based algorithm for optimizing stock trading and portfolio management 182
farama-foundation/gymnasium-robotics A collection of robotic simulation environments for reinforcement learning 585
ahq1993/multimodal-deep-q-network-for-social-human-robot-interaction A deep reinforcement learning system designed to enable robots to acquire social interaction skills through multimodal interactions with humans. 14
tristandeleu/pytorch-maml-rl Replication of Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks in PyTorch for reinforcement learning tasks 830
jderobot/roboticsacademy An open-source platform for learning robotics and related technologies through hands-on exercises 323
google-research/big_transfer Pre-trained models and code for fine-tuning image recognition tasks using deep learning frameworks 1,516
jay15summer/two-stage-tradaboost.r2 An implementation of a boosting-based transfer learning algorithm for regression tasks. 44
ikostrikov/jaxrl Provides JAX implementations of various reinforcement learning algorithms with continuous action spaces. 640
google-deepmind/meltingpot Assesses generalization of multi-agent reinforcement learning algorithms to novel social situations 637
araffin/rl-tutorial-jnrr19 A tutorial project providing an introduction to reinforcement learning with Stable Baselines3 620