UWM-JEPA uses a density-matrix latent and unitary predictor in JEPA to preserve joint-state spectrum during blind rollouts, achieving 0.77 accuracy on a five-step hidden-velocity task versus 0.53 for an LSTM baseline.
Deep recurrent q-learning for partially observable mdps.arXiv preprint arXiv:1507.06527
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Deep Reinforcement Learning has yielded proficient controllers for complex tasks. However, these controllers have limited memory and rely on being able to perceive the complete game screen at each decision point. To address these shortcomings, this article investigates the effects of adding recurrency to a Deep Q-Network (DQN) by replacing the first post-convolutional fully-connected layer with a recurrent LSTM. The resulting \textit{Deep Recurrent Q-Network} (DRQN), although capable of seeing only a single frame at each timestep, successfully integrates information through time and replicates DQN's performance on standard Atari games and partially observed equivalents featuring flickering game screens. Additionally, when trained with partial observations and evaluated with incrementally more complete observations, DRQN's performance scales as a function of observability. Conversely, when trained with full observations and evaluated with partial observations, DRQN's performance degrades less than DQN's. Thus, given the same length of history, recurrency is a viable alternative to stacking a history of frames in the DQN's input layer and while recurrency confers no systematic advantage when learning to play the game, the recurrent net can better adapt at evaluation time if the quality of observations changes.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Intervention on a fixed-size recurrent state enables contextual control in sequential decisions without memory growth or direct context input.
ARL lifts states into signature-augmented manifolds and employs self-consistent proxies of future path-laws to enable deterministic expected-return evaluation while preserving contraction mappings in jump-diffusion environments.
ALFWorld aligns text-based and embodied visual environments so agents can learn abstract policies in TextWorld that transfer to better performance on ALFRED tasks than visual-only training.
A decoupled estimator combining gated dynamics learning and recursive Kalman filtering improves robustness of pre-trained MARL policies under stale observations and message loss.
Belief-state RWKV maintains an uncertainty-aware recurrent state for RL policies in partial observability and shows modest gains over standard recurrent baselines in a pilot with observation noise.
A tutorial framing deep learning as a complement to optimization for sequential decision-making under uncertainty, with applications in supply chains, healthcare, and energy.
citing papers explorer
-
Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering
A decoupled estimator combining gated dynamics learning and recursive Kalman filtering improves robustness of pre-trained MARL policies under stale observations and message loss.