DreamerV2 reaches human-level performance on 55 Atari games by learning behaviors inside a separately trained discrete-latent world model.
Implicit Quantile Networks for Distributional Reinforcement Learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN. We achieve this by using quantile regression to approximate the full quantile function for the state-action return distribution. By reparameterizing a distribution over the sample space, this yields an implicitly defined return distribution and gives rise to a large class of risk-sensitive policies. We demonstrate improved performance on the 57 Atari 2600 games in the ALE, and use our algorithm's implicitly defined distributions to study the effects of risk-sensitive policies in Atari games.
representative citing papers
Flow matching critics outperform monolithic ones in RL by 2x performance and 5x sample efficiency via test-time error recovery through integration and multi-point velocity supervision that preserves feature plasticity.
DVPO learns token-level value distributions and uses asymmetric risk regularization to contract lower tails while expanding upper tails, outperforming PPO and GRPO under noisy supervision in dialogue, math, and QA tasks.
A neural network scheme approximates risk and policies for dynamic risk-sensitive MDPs using synthetic data based on mean-variance risk estimation.
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.
-
What Does Flow Matching Bring To TD Learning?
Flow matching critics outperform monolithic ones in RL by 2x performance and 5x sample efficiency via test-time error recovery through integration and multi-point velocity supervision that preserves feature plasticity.
-
DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training
DVPO learns token-level value distributions and uses asymmetric risk regularization to contract lower tails while expanding upper tails, outperforming PPO and GRPO under noisy supervision in dialogue, math, and QA tasks.
-
A Scheme for Dynamic Risk-Sensitive Sequential Decision Making
A neural network scheme approximates risk and policies for dynamic risk-sensitive MDPs using synthetic data based on mean-variance risk estimation.