paper-with-me

Papers

Exploration by Random Network Distillation

2018-10-30 · ICLR 2019 · Yuri Burda, Harrison Edwards, Amos Storkey, Oleg Klimov

We introduce an exploration bonus for deep reinforcement learning methods that is easy to implement and adds minimal overhead to the computation performed. The bonus is the error of a neural network predicting features of the observations given by a fixed randomly initialized neural network. We also introduce a method to flexibly combine intrinsic and extrinsic rewards. We find that the random network distillation (RND) bonus combined with this increased flexibility enables significant progress on several hard exploration Atari games. In particular we establish state of the art performance on Montezuma's Revenge, a game famously difficult for deep reinforcement learning methods. To the best of our knowledge, this is the first method that achieves better than average human performance on this game without using demonstrations or having access to the underlying state of the game, and occasionally completes the first level.

📄 PDF Abstract BibTeX arXiv:1810.12894

Code (22)

openai/random-network-distillation 공식 구현 tf
DuaneNielsen/rnd pytorch
Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation- tf
Justkim/random-network-distillation-pytorch pytorch
LeejwUniverse/RL_Exploration_Pytorch pytorch
Narsil/rl-baselines pytorch
alirezakazemipour/ppo-rnd pytorch
bacdavid/RND-O
balloch/rl-exploration-transfer pytorch
forevergj/multithreading_ppo_RND pytorch
jakegrigsby/supersonic tf
jcwleo/random-network-distillation-pytorch pytorch
jhare96/reinforcement-learning tf
kngwyu/intrinsic-rewards pytorch
lgerrets/rl18-curiosity
michalnand/reinforcement_learning pytorch
microsoft/strategically_efficient_rl tf
opendilab/DI-engine/blob/main/ding/reward_model/rnd_reward_model.py pytorch
riveSunder/carle pytorch
riveSunder/moving_in_morley pytorch
rle-foundation/rlexplore jax
uoe-agents/derl pytorch

Tasks

Atari GamesDeep Reinforcement LearningMontezuma's Revengereinforcement-learningReinforcement LearningReinforcement Learning (RL)Unsupervised Reinforcement Learning

Similar Papers 제목 키워드 기반

Combining Experience Replay with Exploration by Random Network Distillation

2019-05-18 · Francesco Sovrano

Our work is a simple extension of the paper "Exploration by Random Network Distillation". More in detail, we show how to efficiently combine Intrinsic Rewards with Experience Replay in order to achieve more efficient and…

Atari GamesMontezuma's Revenge

Exploration and Anti-Exploration with Distributional Random Network Distillation

2024-01-18 · Kai Yang, Jian Tao, Jiafei Lyu, Xiu Li

Exploration remains a critical issue in deep reinforcement learning for an agent to attain high returns in unknown environments. Although the prevailing exploration Random Network Distillation (RND) algorithm has been de…

D4RLDeep Reinforcement Learning

Towards Better Sample Efficiency in Multi-Agent Reinforcement Learning via Exploration

2025-03-17 · Amir Baghi, Jens Sjölund, Joakim Bergdahl, Linus Gisslén 외

Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often demand extensive training time. For instance, the state-of-the-art method TiZ…

Computational EfficiencyMulti-agent Reinforcement Learning

Exploration by Random Network Distillation

2022-01-17 · ICLR Track Blog 2022 5 · Anonymous

We introduce an exploration bonus for deep reinforcement learning methods that is easy to implement and adds minimal overhead to the computation performed. The bonus is the error of a neural network predicting features o…

Atari GamesDeep Reinforcement LearningMontezuma's Revengereinforcement-learning+2

Anti-Exploration by Random Network Distillation

2023-01-31 · Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov, Sergey Kolesnikov

Despite the success of Random Network Distillation (RND) in various domains, it was shown as not discriminative enough to be used as an uncertainty estimator for penalizing out-of-distribution actions in offline reinforc…

D4RL