Switching Isotropic and Directional Exploration with Parameter Space Noise in Deep Reinforcement Learning Sep 18, 2018 Deep Reinforcement Learning OpenAI Gym
— Unverified Visual Transfer between Atari Games using Competitive Reinforcement Learning Sep 2, 2018 Atari Games Deep Reinforcement Learning
Code Code Available GeneSys: Enabling Continuous Learning through Neural Network Evolution in Hardware Aug 3, 2018 CPU GPU
— Unverified FuzzerGym: A Competitive Framework for Fuzzing and Learning Jul 19, 2018 Deep Reinforcement Learning Fault Detection
— Unverified Online Robust Policy Learning in the Presence of Unknown Adversaries Jul 16, 2018 Deep Reinforcement Learning OpenAI Gym
— Unverified Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Network Jun 14, 2018 OpenAI Gym reinforcement-learning
— Unverified Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces Jun 8, 2018 Atari Games Gaussian Processes
— Unverified Deep Reinforcement Learning for General Video Game AI Jun 6, 2018 Atari Games Benchmarking
Code Code Available BindsNET: A machine learning-oriented spiking neural networks library in Python Jun 4, 2018 BIG-bench Machine Learning CPU
Code Code Available Intelligent Trainer for Model-Based Reinforcement Learning May 24, 2018 model Model-based Reinforcement Learning
Code Code Available Advances in Experience Replay May 15, 2018 OpenAI Gym
Code Code Available GAN Q-learning May 13, 2018 Distributional Reinforcement Learning OpenAI Gym
Code Code Available Deep Reinforcement Learning for Playing 2.5D Fighting Games May 5, 2018 Deep Reinforcement Learning OpenAI Gym
Code Code Available State Distribution-aware Sampling for Deep Q-learning Apr 23, 2018 Atari Games OpenAI Gym
— Unverified Structured Evolution with Compact Architectures for Scalable Policy Optimization Apr 6, 2018 OpenAI Gym Text-to-Image Generation
— Unverified Recurrent Predictive State Policy Networks Mar 5, 2018 OpenAI Gym Reinforcement Learning
Code Code Available Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research Feb 26, 2018 continuous-control Continuous Control
Code Code Available Exploring Deep Recurrent Models with Reinforcement Learning for Molecule Design Jan 1, 2018 Drug Discovery OpenAI Gym
— Unverified Neuron as an Agent Jan 1, 2018 counterfactual Multi-agent Reinforcement Learning
— Unverified Combining Model-based and Model-free RL via Multi-step Control Variates Jan 1, 2018 continuous-control Continuous Control
— Unverified HoME: a Household Multimodal Environment Nov 29, 2017 OpenAI Gym reinforcement-learning
— Unverified A novel DDPG method with prioritized experience replay Oct 1, 2017 continuous-control Continuous Control
Code Code Available MDP environments for the OpenAI Gym Sep 26, 2017 OpenAI Gym reinforcement-learning
Code Code Available Closing the loop between neural network simulators and the OpenAI Gym Sep 17, 2017 OpenAI Gym reinforcement-learning
— Unverified Benchmark Environments for Multitask Learning in Continuous Domains Aug 14, 2017 Lifelong learning OpenAI Gym
Code Code Available Investigating Reinforcement Learning Agents for Continuous State Space Environments Aug 8, 2017 OpenAI Gym Q-Learning
— Unverified Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning Jun 1, 2017 continuous-control Continuous Control
— Unverified Non-Markovian Control with Gated End-to-End Memory Policy Networks May 31, 2017 OpenAI Gym Reinforcement Learning
— Unverified AIXIjs: A Software Demo for General Reinforcement Learning May 22, 2017 General Reinforcement Learning OpenAI Gym
Code Code Available Beating Atari with Natural Language Guided Reinforcement Learning Apr 18, 2017 Atari Games Deep Reinforcement Learning
Code Code Available Towards Generalization and Simplicity in Continuous Control Mar 8, 2017 continuous-control Continuous Control
Code Code Available Collaborative Deep Reinforcement Learning Feb 19, 2017 Deep Reinforcement Learning Knowledge Distillation
Code Code Available 