Papers › #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

15 Nov 2016NeurIPS 2017 12arXiv:1611.04717archive 2025-07-28

Haoran Tang, Rein Houthooft, Davis Foote, Adam Stooke, Xi Chen, Yan Duan, John Schulman, Filip De Turck, Pieter Abbeel

Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision processes (MDPs). It is generally thought that count-based methods cannot be applied in high-dimensional state spaces, since most states will only occur once. Recent deep RL exploration strategies are able to deal with high-dimensional continuous state spaces through complex heuristics, often relying on optimism in the face of uncertainty or intrinsic motivation. In this work, we describe a surprising finding: a simple generalization of the classic count-based approach can reach near state-of-the-art performance on various high-dimensional and/or continuous deep RL benchmarks. States are mapped to hash codes, which allows to count their occurrences with a hash table. These counts are then used to compute a reward bonus according to the classic count-based exploration theory. We find that simple hash functions can achieve surprisingly good results on many challenging tasks. Furthermore, we show that a domain-dependent learned hash code may further improve these results. Detailed analysis reveals important aspects of a good hash function: 1) having appropriate granularity and 2) encoding information relevant to solving the MDP. This exploration strategy achieves near state-of-the-art performance on both continuous control tasks and Atari 2600 games, hence providing a simple yet powerful baseline for solving MDPs that require considerable exploration.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

clementbernardd/Count-Based-Exploration mentioned on GitHubpytorchSyntology: not harvested report
nhynes/abc mentioned on GitHubpytorchSyntology: not harvested report
uoe-agents/derl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Curiosity-driven Exploration by Self-supervised Prediction (arXiv:1705.05363; that paper's own run record: 16 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 16 unverified) and Exploration by Random Network Distillation (arXiv:1810.12894; that paper's own run record: 31 ran (of which 12 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Atari GamesContinuous ControlDeep Reinforcement LearningReinforcement LearningReinforcement Learning (RL)continuous-controlreinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Freeway TRPO-hash Score 34.0 #1 of 59 Archive leaderboard report
Atari Games Atari 2600 Frostbite TRPO-hash Score 5214.0 #15 of 53 Archive leaderboard report
Atari Games Atari 2600 Montezuma's Revenge TRPO-hash Score 75 #29 of 50 Archive leaderboard report
Atari Games Atari 2600 Venture TRPO-hash Score 445.0 #23 of 55 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections