REVIEW 2 cited by
Prioritized Sequence Experience Replay
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Experience replay is widely used in deep reinforcement learning algorithms and allows agents to remember and learn from experiences from the past. In an effort to learn more efficiently, researchers proposed prioritized experience replay (PER) which samples important transitions more frequently. In this paper, we propose Prioritized Sequence Experience Replay (PSER) a framework for prioritizing sequences of experience in an attempt to both learn more efficiently and to obtain better performance. We compare the performance of PER and PSER sampling techniques in a tabular Q-learning environment and in DQN on the Atari 2600 benchmark. We prove theoretically that PSER is guaranteed to converge faster than PER and empirically show PSER substantially improves upon PER.
Forward citations
Cited by 2 Pith papers
-
EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learning
EVaDE inserts three Gaussian-dropout convolutional layers into SimPLe reward models, raising mean human-normalized Atari 100K score from 0.525 to 0.682 in the paper's runs.
-
Reward Prediction Error Prioritisation in Experience Replay: The RPE-PER Method
RPE-PER prioritises replay buffer samples by the absolute error between a learned reward model and the actual reward, and reports improved continuous-control RL performance in MuJoCo benchmarks.
Discussion (0). Continue with ORCID to comment.