Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting

Abstract

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong learning setting, in which an agent is faced with multiple consecutive tasks over its lifetime, reusing information from previously seen tasks can substantially accelerate the learning of new tasks. We provide a novel method for lifelong policy gradient learning that trains lifelong function approximators directly via policy gradients, allowing the agent to benefit from accumulated knowledge throughout the entire training process. We show empirically that our algorithm learns faster and converges to better policies than single-task and lifelong learning baselines, and completely avoids catastrophic forgetting on a variety of challenging domains.

arXiv commentTo appear in Advances in Neural Information Processing Systems 33 (NeurIPS-20)

References in corpus (12)

• Continuous control with deep reinforcement learning
• Overcoming catastrophic forgetting in neural networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Trust Region Policy Optimization
• Continual Learning Through Synaptic Intelligence
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
• Progress & Compress: A scalable framework for continual learning
• Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
• On Quadratic Penalties in Elastic Weight Consolidation
• Functional Regularisation for Continual Learning with Gaussian Processes
• Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL

Cited by in corpus (4)

• Continual World: A Robotic Benchmark For Continual Reinforcement Learning
• Structure in Deep Reinforcement Learning: A Survey and Open Problems
• OER: Offline Experience Replay for Continual Offline Reinforcement Learning
• System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games