Divide-and-Conquer Reinforcement Learning
Explore this paper's citation graph
Summary
The results show that divide-and-conquer RL greatly outperforms conventional policy gradient methods on challenging grasping, manipulation, and locomotion tasks, and exceeds the performance of a variety of prior methods.
- Type
- preprint
- Published
- 2017-11-27
- Cited by
- 136
- References
- 24
- Access
- Open access
- OpenAlex
- https://openalex.org/W2768578623
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:997870
Keywords
Divide and conquer algorithms, Reinforcement learning, Computer science, Bellman equation, Artificial intelligence
References
- Playing Atari with Deep Reinforcement Learning
- Learning throwing and catching skills
- Guided Policy Search
- A Natural Policy Gradient
- Human-level control through deep reinforcement learning
- MuJoCo: A physics engine for model-based control
- Interactive Control of Diverse Complex Characters with Neural Networks
- Combining the benefits of function approximation and trajectory optimization
- Optimal control with learned local models: Application to dexterous manipulation
- Towards Generalization and Simplicity in Continuous Control
- Data-efficient Deep Reinforcement Learning for Dexterous Manipulation
- Emergence of Locomotion Behaviours in Rich Environments
- Overcoming Exploration in Reinforcement Learning with Demonstrations
- Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
- Distral: Robust multitask reinforcement learning
- End-to-End Training of Deep Visuomotor Policies
- Purposive Behavior Acquisition for a Real Robot by Vision-Based Reinforcement Learning
- Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
- OpenAI Gym
- Experiments with Hierarchical Reinforcement Learning of Multiple Grasping Policies
Cited by
- Hindsight policy gradients
- Learning by Playing - Solving Sparse Reward Tasks from Scratch
- A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials
- Information asymmetry in KL-regularized RL
- Intelligent Control of a Quadrotor with Proximal Policy Optimization Reinforcement Learning
- Composing Complex Skills by Learning Transition Policies
- Distilling Policy Distillation
- Exploiting Hierarchy for Learning and Transfer in KL-regularized RL
- Policy Gradient Search: Online Planning and Expert Iteration without Search Trees
- Guided Meta-Policy Search
- KeyIn: Discovering Subgoal Structure with Keyframe-based Video Prediction
- Don't Forget Your Teacher: A Corrective Reinforcement Learning Framework
- On the Weaknesses of Reinforcement Learning for Neural Machine Translation
- GAPLE: Generalizable Approaching Policy LEarning for Robotic Object Searching in Indoor Environment
- An Information-theoretic On-line Learning Principle for Specialization in Hierarchical Decision-Making Systems
- A review on Deep Reinforcement Learning for Fluid Mechanics
- Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
- Bottom-Up Meta-Policy Search
- Divide-and-Conquer Adversarial Learning for High-Resolution Image and Video Enhancement
- Hierarchical Expert Networks for Meta-Learning
Related papers
- Human-level control through deep reinforcement learning
- A Minimalist Approach to Offline Reinforcement Learning
- Offline Reinforcement Learning as One Big Sequence Modeling Problem
- ACERAC: Efficient Reinforcement Learning in Fine Time Discretization
- Efficient (Soft) Q-Learning for Text Generation with Limited Good Data
- PMA-DRL: A parallel model-augmented framework for deep reinforcement learning algorithms
- Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization
- TTR-Based Rewards for Reinforcement Learning with Implicit Model Priors
- SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning