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.
☆40Updated 3 years ago
Related projects: ⓘ
- Pytorch implementation of distributed deep reinforcement learning☆72Updated 2 years ago
- Datasets for data-driven deep reinforcement learning with PyBullet environments☆143Updated 3 years ago
- PyTorch implementation of Stochastic Latent Actor-Critic(SLAC).☆87Updated last month
- Code accompanying the paper "Better Exploration with Optimistic Actor Critic" (NeurIPS 2019)☆68Updated last year
- PyTorch implementation of the state-of-the-art distributional reinforcement learning algorithm Fully Parameterized Quantile Function (FQF…☆28Updated 3 years ago
- ☆107Updated last year
- pytorch-implementation of Dreamer (Model-based Image RL Algorithm)☆158Updated 2 years ago
- Code for "Learning to Reach Goals via Iterated Supervised Learning"☆76Updated 2 years ago
- Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning☆95Updated 2 years ago
- A collection of RL algorithms written in JAX.☆92Updated 2 years ago
- ☆47Updated 3 years ago
- ☆187Updated last year
- SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning☆119Updated 3 years ago
- ☆79Updated 3 years ago
- Code for MOPO: Model-based Offline Policy Optimization☆169Updated 2 years ago
- MetaGenRL, a novel meta reinforcement learning algorithm. Unlike prior work, MetaGenRL can generalize to new environments that are entire…☆65Updated 4 years ago
- PyTorch implementation of FQF, IQN and QR-DQN.☆158Updated last month
- Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model☆149Updated 3 years ago
- Fast Flexible Replay Buffer Library (Mirror repository of https://gitlab.com/ymd_h/cpprb)☆71Updated 3 months ago
- A Tensorflow implementation of the Option-Critic Architecture☆71Updated 7 years ago
- Arena: A General Evaluation Platform and Building Toolkit for Single/Multi-Agent Intelligence. AAAI 2020.☆101Updated 3 years ago
- Codes accompanying the paper "ROMA: Multi-Agent Reinforcement Learning with Emergent Roles" (ICML 2020 https://arxiv.org/abs/2003.08039)☆148Updated last year
- ☆69Updated 3 months ago
- Revisiting Rainbow☆73Updated 3 years ago
- Soft Actor-Critic☆142Updated 6 years ago
- AGAC: Adversarially Guided Actor-Critic☆47Updated 3 years ago
- Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"☆157Updated 2 years ago
- Explorer is a PyTorch reinforcement learning framework for exploring new ideas.☆88Updated 2 weeks ago
- OpenAI Gym wrapper for the DeepMind Control Suite☆200Updated 4 months ago
- The Reinforcement-Learning-Related Papers of ICLR 2019☆48Updated 5 years ago