ZifanWu

CAL

Code accompanying the paper "Off-Policy Primal-Dual Safe Reinforcement Learning"

Coordinated-PPO

Code accompanying paper "Coordinated Proximal Policy Optimization"

dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

DrQ-v2_in_Jax

fitting-random-labels

Example code for the paper "Understanding deep learning requires rethinking generalization"

Jax_HL_Gauss_loss_on_DMControl

Jax implementation of HL-Gauss loss (from the paper "Stop Regressing: Training Value Functions via Classification for Scalable Deep RL") on top of DRL algorithms.

jaxpruner

MAG

Code accompanying paper "Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning".

mbpo_pytorch

A pytorch reprelication of the model-based reinforcement learning algorithm MBPO

Plan-to-Predict

Code accompanying paper "Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning".

ZifanWu/MAG

Code accompanying paper "Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning".

ZifanWu/CAL

Code accompanying the paper "Off-Policy Primal-Dual Safe Reinforcement Learning"

ZifanWu/Coordinated-PPO

Code accompanying paper "Coordinated Proximal Policy Optimization"

ZifanWu/Plan-to-Predict

Code accompanying paper "Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning".

ZifanWu/DrQ-v2_in_Jax

ZifanWu/dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

ZifanWu/fitting-random-labels

Example code for the paper "Understanding deep learning requires rethinking generalization"

ZifanWu/Jax_HL_Gauss_loss_on_DMControl

Jax implementation of HL-Gauss loss (from the paper "Stop Regressing: Training Value Functions via Classification for Scalable Deep RL") on top of DRL algorithms.

ZifanWu/jaxpruner

ZifanWu/mbpo_pytorch

A pytorch reprelication of the model-based reinforcement learning algorithm MBPO

ZifanWu/mbrl-lib

Library for Model Based RL

ZifanWu/omnisafe

OmniSafe is an infrastructural framework for accelerating SafeRL research.

ZifanWu/pytorch-mopo

re-implementation of the offline model-based RL algorithm MOPO in pytorch

ZifanWu/SAC-Lagrangian

PyTorch implementation of Constrained Reinforcement Learning for Soft Actor Critic Algorithm

ZifanWu/Safe-RL