Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
arXiv:1910.00177
Abstract
In this paper, we aim to develop a simple and scalable reinforcement learning algorithm that uses standard supervised learning methods as subroutines. Our goal is an algorithm that utilizes only simple and convergent maximum likelihood loss functions, while also being able to leverage off-policy data. Our proposed approach, which we refer to as advantage-weighted regression (AWR), consists of two standard supervised learning steps: one to regress onto target values for a value function, and another to regress onto weighted target actions for the policy. The method is simple and general, can accommodate continuous and discrete actions, and can be implemented in just a few lines of code on top of standard supervised learning methods. We provide a theoretical motivation for AWR and analyze its properties when incorporating off-policy data from experience replay. We evaluate AWR on a suite of standard OpenAI Gym benchmark tasks, and show that it achieves competitive performance compared to a number of well-established state-of-the-art RL algorithms. AWR is also able to acquire more effective policies than most off-policy algorithms when learning from purely static datasets with no additional environmental interactions. Furthermore, we demonstrate our algorithm on challenging continuous control tasks with highly complex simulated characters.
References in corpus (3)
Cited by in corpus (64)
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
- How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned
- Conservative Q-Learning for Offline Reinforcement Learning
- Decision Transformer: Reinforcement Learning via Sequence Modeling
- A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems
- D4RL: Datasets for Deep Data-Driven Reinforcement Learning
- MOPO: Model-based Offline Policy Optimization
- A Minimalist Approach to Offline Reinforcement Learning
- Offline Reinforcement Learning with Implicit Q-Learning
- What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study
- Critic Regularized Regression
- AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
- Evolutionary learning of interpretable decision trees
- COMBO: Conservative Offline Model-Based Policy Optimization
- An empirical investigation of the challenges of real-world reinforcement learning
- Phasic Policy Gradient
- COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning
- Learning Deformable Object Manipulation from Expert Demonstrations
- BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning
- Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement
- Learning Robotic Navigation from Experience: Principles, Methods, and Recent Results
- Learning to Reach Goals via Iterated Supervised Learning
- Offline Reinforcement Learning with Reverse Model-based Imagination
- Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
- Model-Based Offline Planning
- Training Agents using Upside-Down Reinforcement Learning
- Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning
- Offline Reinforcement Learning from Images with Latent Space Models
- Reward-Conditioned Policies
- Offline RL Without Off-Policy Evaluation
- Offline Learning from Demonstrations and Unlabeled Experience
- PLAS: Latent Action Space for Offline Reinforcement Learning
- Offline Meta-Reinforcement Learning with Advantage Weighting
- Offline Reinforcement Learning with Value-based Episodic Memory
- Learning and Planning in Complex Action Spaces
- Human-in-the-Loop Imitation Learning using Remote Teleoperation
- ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning
- Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL
- Offline Reinforcement Learning with Soft Behavior Regularization
- TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations
- Semi-supervised reward learning for offline reinforcement learning
- Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback
- Continuous Doubly Constrained Batch Reinforcement Learning
- A Workflow for Offline Model-Free Robotic Reinforcement Learning
- Instabilities of Offline RL with Pre-Trained Neural Representation
- GRAC: Self-Guided and Self-Regularized Actor-Critic
- Offline Reinforcement Learning with Pseudometric Learning
- Reinforcement Learning with Videos: Combining Offline Observations with Interaction
- AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale
- Safe Driving via Expert Guided Policy Optimization
- On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning
- REPAINT: Knowledge Transfer in Deep Reinforcement Learning
- Conservative Data Sharing for Multi-Task Offline Reinforcement Learning
- OER: Offline Experience Replay for Continual Offline Reinforcement Learning
- Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning
- You Only Evaluate Once: a Simple Baseline Algorithm for Offline RL
- Offline Preference-Based Apprenticeship Learning
- On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations
- Neural Lyapunov Model Predictive Control: Learning Safe Global Controllers from Sub-optimal Examples
- Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning
- A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets
- Curriculum Offline Imitation Learning
- Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning
- Quantile Filtered Imitation Learning