Learning Guidance Rewards with Trajectory-space Smoothing
arXiv:2010.12718
Abstract
Long-term temporal credit assignment is an important challenge in deep reinforcement learning (RL). It refers to the ability of the agent to attribute actions to consequences that may occur after a long time interval. Existing policy-gradient and Q-learning algorithms typically rely on dense environmental rewards that provide rich short-term supervision and help with credit assignment. However, they struggle to solve tasks with delays between an action and the corresponding rewarding feedback. To make credit assignment easier, recent works have proposed algorithms to learn dense "guidance" rewards that could be used in place of the sparse or delayed environmental rewards. This paper is in the same vein -- starting with a surrogate RL objective that involves smoothing in the trajectory-space, we arrive at a new algorithm for learning guidance rewards. We show that the guidance rewards have an intuitive interpretation, and can be obtained without training any additional neural networks. Due to the ease of integration, we use the guidance rewards in a few popular algorithms (Q-learning, Actor-Critic, Distributional-RL) and present results in single-agent and multi-agent tasks that elucidate the benefit of our approach when the environmental rewards are sparse or delayed.
arXiv commentNeurIPS 2020 camera-ready
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- Addressing Function Approximation Error in Actor-Critic Methods
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
- Parameter Space Noise for Exploration
- RUDDER: Return Decomposition for Delayed Rewards
- Neural Episodic Control
- A Benchmark Environment Motivated by Industrial Control Problems
- Generative Adversarial Self-Imitation Learning
- Hardware Conditioned Policies for Multi-Robot Transfer Learning
- Learning Self-Imitating Diverse Policies
- Sequence Modeling of Temporal Credit Assignment for Episodic Reinforcement Learning
- Hindsight Credit Assignment