My content of CS294 Deep Reinforcement Learning course, conduced by Sergey Levine from UC Berkeley.
-
Updated
Jan 15, 2018 - Python
My content of CS294 Deep Reinforcement Learning course, conduced by Sergey Levine from UC Berkeley.
PyTorch implementation of "Sample-efficient Imitation Learning via Generative Adversarial Nets"
Contains PyTorch Implementation of the following off policy actor critic algorithms
Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms
A novel method to incorporate existing policy (Rule-based control) with Reinforcement Learning.
Sample Policy Gradient
An Optimistic Approach to the Q-Network Error in Actor-Critic Methods
PyTorch implementation of our work: "Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning"
A RL agent that learns to play doom's deadly corridor based on DDQN and PER.
Off-Policy Correction for Actor-Critic Algorithms in Deep Reinforcement Learning
Stochastic Weighted Twin Delayed Deep Deterministic Policy Gradient (SWTD3)
TensorFlow implementation of "Sample-efficient Imitation Learning via Generative Adversarial Nets"
PyTorch implementation of our work: "Where is the Grass Greener? Revisiting Generalized Policy Iteration for Offline Reinforcement Learning"
PyTorch implementation of our work: "Optimality Inductive Biases and Agnostic Guidelines for Offline Reinforcement Learning"
PyTorch-implementation-DICE-algorithms
Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning
Collection of codes pertaining to my research in model-free RL algorithms.
PyTorch implementation of our work: "Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning"
PyTorch implementation of "Sample-efficient Imitation Learning via Generative Adversarial Nets"
TensorFlow implementation of "Sample-efficient Imitation Learning via Generative Adversarial Nets"
Add a description, image, and links to the off-policy topic page so that developers can more easily learn about it.
To associate your repository with the off-policy topic, visit your repo's landing page and select "manage topics."