Hacker News new | past | comments | ask | show | jobs | submit | from login
Learning State Abstractions for Long-Horizon Planning (bair.berkeley.edu)
3 points by jonbaer 6 days ago | past | discuss
Learning State Abstractions for Long-Horizon Planning (bair.berkeley.edu)
43 points by headalgorithm 7 days ago | past | 1 comment
Adapting on the Fly to Test Time Distribution Shift (bair.berkeley.edu)
1 point by xzvf 8 days ago | past | discuss
EvolveGraph: Dynamic Neural Relational Reasoning for Interacting Systems (bair.berkeley.edu)
4 points by jonbaer 8 days ago | past | discuss
Training on Test Inputs with Amortized Conditional Normalized Maximum Likelihood (bair.berkeley.edu)
2 points by atg_abhishek 11 days ago | past | discuss
Adapting on the Fly to Test Time Distribution Shift (bair.berkeley.edu)
1 point by rohitsohlotwork 21 days ago | past
Adapting on the Fly to Test Time Distribution Shift (bair.berkeley.edu)
1 point by jonbaer 22 days ago | past
Reinforcement learning is supervised learning on optimized data (bair.berkeley.edu)
241 points by jonbaer 44 days ago | past | 18 comments
Reinforcement learning is supervised learning on optimized data (bair.berkeley.edu)
2 points by headalgorithm 45 days ago | past
Plan2Explore: Active Model-Building for Visual Reinforcement Learning (bair.berkeley.edu)
1 point by headalgorithm 51 days ago | past
Plan2Explore: Active Model-Building for Visual Reinforcement Learning (bair.berkeley.edu)
6 points by jonbaer 52 days ago | past
Active Model-Building for Self-Supervised Visual Reinforcement Learning (bair.berkeley.edu)
1 point by headalgorithm 53 days ago | past
Plan2Explore: Active Model-Building for Self-Supervised Visual RL (bair.berkeley.edu)
2 points by atg_abhishek 53 days ago | past
Accelerating Online Reinforcement Learning with Offline Datasets (bair.berkeley.edu)
3 points by MindGods 78 days ago | past
Estimating the fatality rate is difficult but doable with better data (bair.berkeley.edu)
1 point by MindGods 3 months ago | past
Exploring Exploration: Comparing Children with RL Agents in Unified Environments (bair.berkeley.edu)
1 point by jonbaer 4 months ago | past
Exploring Exploration: Comparing Children with RL Agents in Unified Environments (bair.berkeley.edu)
2 points by umangkeshri 4 months ago | past
Can RL from Pixels Be as Efficient as RL from State? (bair.berkeley.edu)
2 points by MindGods 4 months ago | past
Decentralized Reinforcement Learning (bair.berkeley.edu)
61 points by MindGods 4 months ago | past | 13 comments
Speeding Up Transformer Training and Inference by Increasing Model Size (bair.berkeley.edu)
3 points by bjourne 5 months ago | past
D4RL: Building Better Benchmarks for Offline Reinforcement Learning (bair.berkeley.edu)
1 point by jonbaer 5 months ago | past
D4RL: Building Better Benchmarks for Offline Reinforcement Learning (bair.berkeley.edu)
1 point by MindGods 5 months ago | past
Open Compound Domain Adaptation (bair.berkeley.edu)
2 points by headalgorithm 5 months ago | past
OmniTact: A Multi-Directional High-Resolution Touch Sensor (bair.berkeley.edu)
1 point by jonbaer 6 months ago | past
When Recurrent Models Don't Need to Be Recurrent (2018) (bair.berkeley.edu)
1 point by pizza 6 months ago | past
Unsupervised Meta-Learning: Learning to Learn Without Supervision (bair.berkeley.edu)
2 points by BERTHart 6 months ago | past
Four Novel Approaches to Manipulating Fabric (bair.berkeley.edu)
2 points by modo_ 6 months ago | past
Unsupervised Meta-Learning: Learning to Learn Without Supervision (bair.berkeley.edu)
2 points by jonbaer 7 months ago | past
Making Decision Trees Accurate Again (bair.berkeley.edu)
4 points by jonbaer 7 months ago | past
Physically Realistic Attacks on Deep Reinforcement Learning (bair.berkeley.edu)
4 points by jonbaer 8 months ago | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: