Pre-training with non-expert human demonstration for deep reinforcement learning
Explore this paper's citation graph
Summary
This work improves data efficiency in deep RL by addressing one of the two learning goals, feature learning, using supervised learning to pre-train on a small set of non-expert human demonstrations and empirically evaluate the approach using the asynchronous advantage actor-critic algorithms in the Atari domain.
- Type
- article
- Published
- 2018-12-21
- Cited by
- 27
- References
- 45
- Access
- Open access
- OpenAlex
- https://openalex.org/W2906669385
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:56657880
Keywords
Reinforcement learning, Leverage (statistics), Deep learning, Raw data, Feature learning
References
- Faster reinforcement learning after pretraining deep networks to predict state dynamics
- Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping
- A survey of robot learning from demonstration
- Transfer Learning for Reinforcement Learning Domains: A Survey
- Policy Transfer using Reward Shaping
- The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training
- ImageNet Large Scale Visual Recognition Challenge
- Reinforcement Learning: An Introduction
- Human-level control through deep reinforcement learning
- The Arcade Learning Environment: An Evaluation Platform for General Agents
- A Survey on Transfer Learning
- Mastering the game of Go with deep neural networks and tree search
- Deep Belief Nets as Function Approximators for Reinforcement Learning
- Deep Direct Reinforcement Learning for Financial Signal Representation and Trading
- ViZDoom: A Doom-based AI research platform for visual reinforcement learning
- Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification
- Learning to Navigate in Complex Environments
- Policy Distillation
- Towards Knowledge Transfer in Deep Reinforcement Learning
- Deep learning for healthcare: review, opportunities and challenges
Cited by
- Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset
- Q-Learning for Continuous Actions with Cross-Entropy Guided Policies
- Jointly Pre-training with Supervised, Autoencoder, and Value Losses for Deep Reinforcement Learning
- Integrating Machine Learning with Human Knowledge
- Learning the aerodynamic design of supercritical airfoils through deep reinforcement learning
- Self-Imitation Learning in Sparse Reward Settings
- Autonomous Curriculum Generation for Self-Learning Agents
- Improving reinforcement learning with human assistance: an argument for human subject studies with HIPPO Gym
- Special issue on adaptive and learning agents 2018
- Interactive Human–Robot Skill Transfer: A Review of Learning Methods and User Experience
- Lucid dreaming for experience replay: refreshing past states with the current policy
- Pre-training with asynchronous supervised learning for reinforcement learning based autonomous driving
- Multifeature Fusion Human Motion Behavior Recognition Algorithm Using Deep Reinforcement Learning
- Reinforcement Learning-Based Fleet Dispatching for Greenhouse Gas Emission Reduction in Open-Pit Mining Operations
- Exploring Adaptive MCTS with TD Learning in miniXCOM
- An Empirical Study of Artifacts and Security Risks in the Pre-trained Model Supply Chain
- Expert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning
- Multi-evidence learning for medical diagnosis
- Minimizing Human Assistance: Augmenting a Single Demonstration for Deep Reinforcement Learning
- Adaptive Compliant Robot Control with Failure Recovery for Object Press-Fitting
Related papers
No related papers recorded.