DreamerV2 reaches human-level performance on 55 Atari games by learning behaviors inside a separately trained discrete-latent world model.
hub
Distributed Prioritized Experience Replay
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
We propose a distributed architecture for deep reinforcement learning at scale, that enables agents to learn effectively from orders of magnitude more data than previously possible. The algorithm decouples acting from learning: the actors interact with their own instances of the environment by selecting actions according to a shared neural network, and accumulate the resulting experience in a shared experience replay memory; the learner replays samples of experience and updates the neural network. The architecture relies on prioritized experience replay to focus only on the most significant data generated by the actors. Our architecture substantially improves the state of the art on the Arcade Learning Environment, achieving better final performance in a fraction of the wall-clock training time.
hub tools
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
OpenAI Five achieved superhuman performance in Dota 2 by defeating the world champions using scaled self-play reinforcement learning.
Rollout-level advantage-prioritized experience replay for GRPO recycles high-advantage individual rollouts with age eviction and fresh-anchored batches to outperform standard GRPO on math benchmarks, with gains increasing with model size.
A deep reinforcement learning co-optimization framework is developed for jointly sizing solar-battery hybrids and determining their multi-market bidding strategies under stochastic weather and price conditions.
A method trains discrete diffusion policies for combinatorial RL by matching to a PMD-regularized target distribution, reporting SOTA performance and sample efficiency on DNA generation, macro-action, and multi-agent benchmarks.
Effective data transferred from pre-training to fine-tuning is described by a power law in model parameter count and fine-tuning dataset size, acting like a multiplier on the fine-tuning data.
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.
Extends DAE theory to POMDPs with minimal changes and introduces discrete latent dynamics to cut computational cost, with ALE experiments showing scalability and retained sample efficiency.
A multi-agent RL framework for unlabeled multi-robot planning that uses velocity obstacle projections to guarantee collision-free trajectories applicable to arbitrary robot models.
RCRC uses untrained random CNNs and reservoir computing plus evolution strategies to reach claimed state-of-the-art scores in reinforcement learning tasks while avoiding data storage and heavy training.
Deep RL agent trained on generated global routing instances outperforms sequential A* search.
citing papers explorer
-
Mastering Atari with Discrete World Models
DreamerV2 reaches human-level performance on 55 Atari games by learning behaviors inside a separately trained discrete-latent world model.
-
Dota 2 with Large Scale Deep Reinforcement Learning
OpenAI Five achieved superhuman performance in Dota 2 by defeating the world champions using scaled self-play reinforcement learning.
-
Rollout-Level Advantage-Prioritized Experience Replay for GRPO
Rollout-level advantage-prioritized experience replay for GRPO recycles high-advantage individual rollouts with age eviction and fresh-anchored batches to outperform standard GRPO on math benchmarks, with gains increasing with model size.
-
Optimal design of solar-battery hybrid resources considering multi-market participation under weather and price uncertainty
A deep reinforcement learning co-optimization framework is developed for jointly sizing solar-battery hybrids and determining their multi-market bidding strategies under stochastic weather and price conditions.
-
Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces
A method trains discrete diffusion policies for combinatorial RL by matching to a PMD-regularized target distribution, reporting SOTA performance and sample efficiency on DNA generation, macro-action, and multi-agent benchmarks.
-
Scaling Laws for Transfer
Effective data transferred from pre-training to fine-tuning is described by a power law in model parameter count and fine-tuning dataset size, acting like a multiplier on the fine-tuning data.
-
Language Models (Mostly) Know What They Know
Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.
-
A General Language Assistant as a Laboratory for Alignment
Ranked preference modeling outperforms imitation learning for language model alignment and scales more favorably with model size.
-
Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning
Extends DAE theory to POMDPs with minimal changes and introduces discrete latent dynamics to cut computational cost, with ALE experiments showing scalability and retained sample efficiency.
-
Learning Safe Unlabeled Multi-Robot Planning with Motion Constraints
A multi-agent RL framework for unlabeled multi-robot planning that uses velocity obstacle projections to guarantee collision-free trajectories applicable to arbitrary robot models.
-
Convolutional Reservoir Computing for World Models
RCRC uses untrained random CNNs and reservoir computing plus evolution strategies to reach claimed state-of-the-art scores in reinforcement learning tasks while avoiding data storage and heavy training.
-
A Deep Reinforcement Learning Approach for Global Routing
Deep RL agent trained on generated global routing instances outperforms sequential A* search.