Develops and tests the first effective safeguard for analytic gradient-based provably safe RL, showing safe training on three control tasks without performance loss.
Data-efficient Deep Reinforcement Learning for Dexterous Manipulation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Deep learning and reinforcement learning methods have recently been used to solve a variety of problems in continuous control domains. An obvious application of these techniques is dexterous manipulation tasks in robotics which are difficult to solve using traditional control theory or hand-engineered approaches. One example of such a task is to grasp an object and precisely stack it on another. Solving this difficult and practically relevant problem in the real world is an important long-term goal for the field of robotics. Here we take a step towards this goal by examining the problem in simulation and providing models and techniques aimed at solving it. We introduce two extensions to the Deep Deterministic Policy Gradient algorithm (DDPG), a model-free Q-learning based method, which make it significantly more data-efficient and scalable. Our results show that by making extensive use of off-policy data and replay, it is possible to find control policies that robustly grasp objects and stack them. Further, our results hint that it may soon be feasible to train successful stacking policies by collecting interactions on real robots.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Chain-of-thought monitoring detects reward hacking in frontier reasoning models, but strong optimization against the monitor produces obfuscated misbehavior that remains hard to detect.
The DeepMind Control Suite supplies a standardized collection of continuous control tasks with interpretable rewards for benchmarking reinforcement learning agents.
RLFP and the FAC algorithm combine foundation-model priors for policy, value, and rewards to produce sample-efficient robotic RL that reaches 86% real-robot success after one hour and 100% success on 7/8 Meta-world tasks in under 100k frames.
A structured survey of dexterous robotic hand research that reviews hardware, control methods, data resources, and benchmarks while identifying major limitations and future directions.
citing papers explorer
-
Leveraging Analytic Gradients in Provably Safe Reinforcement Learning
Develops and tests the first effective safeguard for analytic gradient-based provably safe RL, showing safe training on three control tasks without performance loss.
-
Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
Chain-of-thought monitoring detects reward hacking in frontier reasoning models, but strong optimization against the monitor produces obfuscated misbehavior that remains hard to detect.
-
DeepMind Control Suite
The DeepMind Control Suite supplies a standardized collection of continuous control tasks with interpretable rewards for benchmarking reinforcement learning agents.
-
Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own
RLFP and the FAC algorithm combine foundation-model priors for policy, value, and rewards to produce sample-efficient robotic RL that reaches 86% real-robot success after one hour and 100% success on 7/8 Meta-world tasks in under 100k frames.
-
Towards Robotic Dexterous Hand Intelligence: A Survey
A structured survey of dexterous robotic hand research that reviews hardware, control methods, data resources, and benchmarks while identifying major limitations and future directions.