Massively Scaling Explicit Policy-conditioned Value Functions
We introduce a scaling strategy for Explicit Policy-Conditioned Value Functions (EPVFs) that significantly improves performance on challenging continuous-control tasks. EPVFs learn a value function V({\theta}) that is explicitly conditioned on the policy parameters, enabling direct gradient-based updates to the parameters of any policy. However, EPVFs at scale struggle with unrestricted parameter growth and efficient exploration in the policy parameter space. To address these issues, we utilize massive parallelization with GPU-based simulators, big batch sizes, weight clipping and scaled peturbations. Our results show that EPVFs can be scaled to solve complex tasks, such as a custom Ant environment, and can compete with state-of-the-art Deep Reinforcement Learning (DRL) baselines like Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC). We further explore action-based policy parameter representations from previous work and specialized neural network architectures to efficiently handle weight-space features, which have not been used in the context of DRL before.
Code (0)
등록된 구현이 없습니다.
Tasks
continuous-controlContinuous ControlDeep Reinforcement LearningEfficient ExplorationGPUSimilar Papers 제목 키워드 기반
Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation
Reinforcement learning is time-consuming for complex tasks due to the need for large amounts of training data. Recent advances in GPU-based simulation, such as Isaac Gym, have sped up data collection thousands of times o…
GPUQ-Learningreinforcement-learningDiffusion Guidance Is a Controllable Policy Improvement Operator
At the core of reinforcement learning is the idea of learning beyond the performance in the data. However, scaling such systems has proven notoriously tricky. In contrast, techniques from generative modeling have proven …
Offline RLMotus2: A Self-Evolving General World Model for Dexterous Manipulation
General embodied agents should perceive, predict, act, evaluate, and improve within a unified system. World models have shown great promise in building such agents, yet existing models typically append an action output h…
Domain AdaptationTest-Time Gradient Guidance of Flow Policies in Reinforcement Learning
Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control. While they are known to scale stably in …
Reinforcement LearningContinuous ControlOffline RLTrust-Region Diffusion Policies for Massively Parallel On-Policy RL
Reinforcement learning with massively parallel simulations has become a standard framework for developing robust, deployable policies; however, most existing approaches still rely on simple Gaussian policy parameterizati…
Reinforcement Learning