filmov
tv
Reinforcement Learning with sparse rewards
Показать описание
In this video I dive into three advanced papers that addres the problem of the sparse reward setting in Deep Reinforcement Learning and pose interesting research directions for mastering unsupervised learning in autonomous agents.
Papers discussed:
Reinforcement Learning with Unsupervised Auxiliary Tasks - DeepMind:
Curiosity Driven Exploration - UC Berkeley:
Hindsight Experience Replay - OpenAI:
If you want to support this channel, here is my patreon link:
Papers discussed:
Reinforcement Learning with Unsupervised Auxiliary Tasks - DeepMind:
Curiosity Driven Exploration - UC Berkeley:
Hindsight Experience Replay - OpenAI:
If you want to support this channel, here is my patreon link:
0:16:01
Reinforcement Learning with sparse rewards
0:02:56
Reward Shaping
0:01:45
Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control
0:01:01
Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
![[Presentation] Action Guidance:](https://i.ytimg.com/vi/jp6VxEK131o/hqdefault.jpg)
0:19:46
[Presentation] Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for RTS Games
0:03:00
Task Specification for Reinforcement Learning on Real Robots Using Sparse Rewards
0:25:18
Overcome Sparse Rewards in Reinforcement Learning
0:13:28
Understanding Reinforcement Learning Environment and Rewards
0:03:00
Revisiting Sparse Rewards for Goal-Reaching Reinforcement Learning
0:14:43
Learning to Generalise in Sparse Reward Navigation Environments
0:27:58
Design the Best Reward Function | Reinforcement Learning Part-6
0:01:17
Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards
0:09:54
Upside-Down Reinforcement Learning
0:16:27
An introduction to Reinforcement Learning
0:30:50
Nearly Minimax Optimal Reward-Free Reinforcement Learning
0:26:46
Reinforcement Learning with TensorFlow and Unity - Pittsburgh ML Summit ‘19
0:26:02
Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions
0:26:03
Reinforcement Learning: Machine Learning Meets Control Theory
0:00:16
Navigating Sparse Rewards in RL
0:55:13
AI Seminar Series 2024: Exploring in Sparse-Reward Domains, Dr. Guni Sharon
0:17:52
Training AI Without Writing A Reward Function, with Reward Modelling
0:00:57
Cooperative Navigation - Sparse Reward Function
0:57:55
MIT 6.S094: Deep Reinforcement Learning
0:19:03
Go-Explore: a New Approach for Hard-Exploration Problems
Комментарии