The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning
원문 초록
We study the multi-step off-policy learning approach to distributional RL. Despite the apparent similarity between value-based RL and distributional RL, our study reveals intriguing and fundamental differences between the two cases in the multi-step setting. We identify a novel notion of path-dependent distributional TD error, which is indispensable for principled multi-step distributional RL. The distinction from the value-based case bears important implications on concepts such as backward-view algorithms. Our work provides the first theoretical guarantees on multi-step off-policy distributional RL algorithms, including results that apply to the small number of existing approaches to multi-step distributional RL. In addition, we derive a novel algorithm, Quantile Regression-Retrace, which leads to a deep RL agent QR-DQN-Retrace that shows empirical improvements over QR-DQN on the Atari-57 benchmark. Collectively, we shed light on how unique challenges in multi-step distributional RL can be addressed both in theory and practice.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
2048: Reinforcement Learning in a Delayed Reward Environment
High-Throughput Distributed Reinforcement Learning via Adaptive Policy Synchronization
Exploring the robustness of TractOracle methods in RL-based tractography
Deep Reinforcement Learning with Gradient Eligibility Traces
AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs
OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
토론
이 논문과 연결된 포럼 글이 아직 없습니다.