microsoft / FQF
FQF(Fully parameterized Quantile Function for distributional reinforcement learning) is a general reinforcement learning framework for Atari games, which can learn to play Atari games automatically by predicting return distribution in the form of a fully parameterized quantile function.
☆42Updated 4 years ago
Alternatives and similar repositories for FQF:
Users that are interested in FQF are comparing it to the libraries listed below
- Pytorch implementation of distributed deep reinforcement learning☆76Updated 2 years ago
- Datasets for data-driven deep reinforcement learning with PyBullet environments☆149Updated 4 years ago
- PyTorch implementation of Stochastic Latent Actor-Critic(SLAC).☆91Updated 9 months ago
- PyTorch implementation of the state-of-the-art distributional reinforcement learning algorithm Fully Parameterized Quantile Function (FQF…☆31Updated 4 years ago
- Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model☆150Updated 4 years ago
- ☆47Updated 4 years ago
- pytorch-implementation of Dreamer (Model-based Image RL Algorithm)☆166Updated 3 months ago
- A Tensorflow implementation of the Option-Critic Architecture☆72Updated 7 years ago
- Keeping track of RL experiments☆161Updated 2 years ago
- Revisiting Rainbow☆74Updated 3 years ago
- Codes accompanying the paper "ROMA: Multi-Agent Reinforcement Learning with Emergent Roles" (ICML 2020 https://arxiv.org/abs/2003.08039)☆160Updated 2 years ago
- Performances of Reinforcement Learning Agents☆53Updated 5 years ago
- SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning☆124Updated 4 years ago
- PyTorch implementation of FQF, IQN and QR-DQN.☆176Updated 9 months ago
- Soft Actor-Critic with advanced features☆50Updated this week
- Pytorch implementation of "FeUdal Networks for Hierarchical Reinforcement Learning" for Montezuma's Revenge☆94Updated 2 years ago
- ☆53Updated 4 years ago
- ☆195Updated 2 years ago
- Code accompanying the paper "Better Exploration with Optimistic Actor Critic" (NeurIPS 2019)☆70Updated last year
- Code for MOPO: Model-based Offline Policy Optimization☆178Updated 2 years ago
- ☆71Updated 5 years ago
- Recurrent continuous reinforcement learning algorithms implemented in Pytorch.☆51Updated 3 years ago
- Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO☆200Updated 2 years ago
- Soft Actor-Critic☆145Updated 7 years ago
- Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"☆161Updated 3 years ago
- Proximal Policy Optimization(PPO) with Intrinsic Curiosity Module(ICM)☆140Updated 6 years ago
- Fast Flexible Replay Buffer Library (Mirror repository of https://gitlab.com/ymd_h/cpprb)☆72Updated 4 months ago
- A Modular Library for Off-Policy Reinforcement Learning with a focus on SafeRL and distributed computing☆133Updated 9 months ago
- ☆91Updated last year
- Implementation of the Option-Critic Architecture on the Atari (ALE) environment☆177Updated 7 years ago