Efficient Solution and Learning of Robust Factored MDPs
"样本效率" 相关文章
Model Predictive Adversarial Imitation Learning for Planning from Observation
Equivariant Volumetric Grasping
Turning Sand to Gold: Recycling Data to Bridge On-Policy and Off-Policy Learning via Causal Bound
EXPO: Stable Reinforcement Learning with Expressive Policies
Reinforcement Learning with Action Chunking
Accelerated Online Reinforcement Learning using Auxiliary Start State Distributions
Causal-Paced Deep Reinforcement Learning
16张H100训26分钟，超越o1-preview！李飞飞等用1K样本，揭秘测试时Scaling
16张H100训26分钟，超越o1-preview！李飞飞等用1K样本，揭秘测试时Scaling
16张H100训26分钟，超越o1-preview，李飞飞等用1K样本，揭秘测试时Scaling
训练1000样本就能超越o1，李飞飞等人画出AI扩展新曲线
流式深度学习终于奏效了！强化学习之父Richard Sutton力荐
科研成果合辑 | CoRL 2024顶会成果速览（上）
Balancing Label Quantity and Quality for Scalable Elicitation
How should we make trade-offs between the quantity and quality of labels used for eliciting knowledge from capable AI systems?
Is Unchecked Churn Holding Back Your AI Performance? This AI Paper Unveils CHAIN: Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn
Scalable Multi-Agent Reinforcement Learning Framework for Efficient Decision-Making in Large-Scale Systems
Scalable oversight as a quantitative rather than qualitative problem
Relational, Object-Centric Agents for Completing Simulated Household Tasks with Wilka Carvalho - #402
