Reward Estimation for Variance Reduction in Deep Reinforcement Learning

2018-05-09 · Joshua Romoff, Peter Henderson, Alexandre Piché, Vincent Francois-Lavet, Joelle Pineau

Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of goal misspecification, randomness in the reward signal, or correlation of the reward with external factors that are not known to the agent. Corruption or stochasticity of the reward signal can be especially problematic in robotics, where goal specification can be particularly difficult for complex tasks. While many variance reduction techniques have been studied to improve the robustness of the RL process, handling such stochastic or corrupted reward structures remains difficult. As an alternative for handling this scenario in model-free RL methods, we suggest using an estimator for both rewards and value functions. We demonstrate that this improves performance under corrupted stochastic rewards in both the tabular and non-linear function approximation settings for a variety of noise types and environments. The use of reward estimation is a robust and easy-to-implement improvement for handling corrupted reward signals in model-free RL.

📄 PDF Abstract BibTeX arXiv:1805.03359

Code (1)

facebookresearch/reward-estimator-corl 공식 구현 pytorch

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Reward-estimation variance elimination in sequential decision processes

2018-11-15 · Sergey Pankov

Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor…

Policy Gradient Methods Reinforcement Learning

Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning

2023-08-28 · Hanhan Zhou, Tian Lan, Vaneet Aggarwal

Offline reinforcement learning aims to utilize datasets of previously gathered environment-action interaction records to learn a policy without access to the real environment. Recent work has shown that offline reinforce…

D4RL Off-policy evaluation OpenAI Gym reinforcement-learning+1

Parameter-free Reduction of the Estimation Bias in Deep Reinforcement Learning for Deterministic Policy Gradients

2021-09-24 · Baturay Saglam, Furkan Burak Mutlu, Dogan Can Cicek, Suleyman Serdar Kozat

Approximation of the value functions in value-based deep reinforcement learning induces overestimation bias, resulting in suboptimal policies. We show that when the reinforcement signals received by the agents have a hig…

continuous-control Continuous Control Deep Reinforcement Learning MuJoCo+2

Stabilizing Policy Gradient Methods via Reward Profiling

2025-11-20 · Shihab Ahmed, El Houcine Bergou, Aritra Dutta, Yue Wang arxiv

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, su…

Reinforcement Learning

Discounted Beta-Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards

2026-03-19 · Haechan Kim, Soohyun Ryu, Gyouk Chu, Doohyuk Jang 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for improving the reasoning capabilities of large language models. However, existing group-based RLVR methods often…