Establishes maximal concentration bounds for stochastic approximation under heavy-tailed Markovian noise, with tails ranging from sub-Gaussian to heavier than Weibull depending on step sizes and contractivity properties, plus a truncation argument for unbounded noise.
hub
Sample Efficient Actor-Critic with Experience Replay
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
abstract
This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several continuous control problems. To achieve this, the paper introduces several innovations, including truncated importance sampling with bias correction, stochastic dueling network architectures, and a new trust region policy optimization method.
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.
Synthetic data augmentation helps channel-mixing time series models but degrades channel-independent ones, with reliable gains only from seasonal-trend generators and gradual schedules in low-resource settings.
Shows entropy coupling limits DSAC on discrete tasks and introduces a generalized actor-critic framework with m-step critics and novel entropy-regularized objectives that perform robustly on Atari.
RGPO replaces importance sampling with a smooth [0,1] acceptance gate in policy gradients, unifying TRPO/PPO/REINFORCE, bounding variance for heavy-tailed ratios, and showing gains in online RLHF experiments.
AWR learns policies via advantage-weighted supervised regression on actions, achieving competitive off-policy performance on Gym tasks and strong results from static data alone.
Introduces polychromic objectives adapted into PPO via vine sampling and modified advantages, showing higher success rates and better coverage under perturbations on BabyAI, Minigrid, and algorithmic tasks.
The authors extend the Almgren-Chriss model to a multi-agent setting and apply deep reinforcement learning to simulate and optimize liquidation strategies under practical constraints.
ASymPO normalizes token losses by average current-policy negative log-probability to restore zero-sum balance in asynchronous LLM RL without behavior information.
Classical agents outperform learning-based ones on MINOS and Stanford 3D Indoor Spaces, with learned agents weaker at collision avoidance and memory but stronger at handling ambiguity and noise.
Dual memory (main plus cache) for replay memory in DRL yields higher scores than single memory across three Gym environments.
Empirical tests in VizDoom show multiple DQN updates per step do not improve performance after learning rate adjustment, with a 4:1 update-to-step ratio optimal before significant degradation.
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.
citing papers explorer
No citing papers match the current filters.