Fisher's Blog

09-30

Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation

10-29

SUNRISE-A-Simple-Unified-Framework-for-Ensemble-Learning-in-Deep-Reinforcement-Learning

10-13

Adapting Auxiliary Losses Using Gradient Similarity & Adaptive Auxiliary Task Weighting for Reinforcement Learning

07-28

Evolution Strategies as a Scalable Alternative to Reinforcement Learning

06-09

Never Give Up: Learning Directed Exploration Strategies

06-03

CURL: Contrastive Unsupervised Representations for Reinforcement Learning

02-18

Squashing

08-22

Recurrent Experience Replay In Distributed Reinforcement Learning

06-14

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

06-12

Diversity is All You Need: Learning Skills without a Reward Function

06-01

Hindsight Experience Replay

03-22

Soft Actor-Critic

02-08

Noisy Networks for Exploration

01-02

Distributed Prioritized Experience Replay

12-26

Clipped Action Policy Gradient

11-13

Reinforcement Learning with Deep Energy-Based Policies

11-12

A Connection Between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models

11-03

Progressive Neural Networks & PathNet

10-09

Deep Exploration via Bootstrapped DQN

10-04

Q-Learning with Continuous Actions