Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / eleurent/rl-agents issues and pull requests

#119 - Display attention lines

Issue - State: open - Opened by IsYang23 5 months ago - 1 comment

#118 - Some issues regarding attention mechanisms

Issue - State: open - Opened by yshichseu 6 months ago - 1 comment

#117 - Some problems in the evaluation.py

Issue - State: open - Opened by Louise599 6 months ago - 1 comment

#116 - Some problems in the evaluation.py

Issue - State: closed - Opened by Louise599 6 months ago

#115 - The problem of reward performance

Issue - State: open - Opened by Louise599 6 months ago - 2 comments

#114 - Display vehicle trajectory

Issue - State: closed - Opened by 6Lackiu 6 months ago - 2 comments

#113 - Algorithmic issues

Issue - State: open - Opened by AHPUymhd 7 months ago - 3 comments

#112 - training problem

Issue - State: closed - Opened by 6Lackiu 7 months ago - 2 comments

#111 - Environment window resizing

Issue - State: open - Opened by Louise599 8 months ago - 1 comment

#110 - Some warnings during operation

Issue - State: open - Opened by Louise599 8 months ago - 1 comment

#109 - Question about rl-agents

Issue - State: open - Opened by HodaHo 10 months ago - 1 comment

#108 - What reward function did you use in IntersectionEnv?

Issue - State: closed - Opened by seominseok00 12 months ago - 2 comments

#107 - How can I obtain the accelaration information of vehicles?

Issue - State: closed - Opened by LemonPasserby almost 1 year ago - 3 comments

#106 - TypeError: must be real number, not NoneType

Issue - State: closed - Opened by seominseok00 about 1 year ago - 11 comments

#105 - Agent compatibility for IntersectionEnv multiagent env

Issue - State: closed - Opened by HeapSoil about 1 year ago - 2 comments

#104 - Improve frontend for the observation carousel

Issue - State: open - Opened by eleurent about 1 year ago

#103 - 'Adam' object has no attribute 'get_updates'

Issue - State: closed - Opened by AashiDutt about 1 year ago - 2 comments

#101 - Fix `AbstractAgent` directory attribute.

Pull Request - State: closed - Opened by Gamenot over 1 year ago - 1 comment

#99 - Use a trained model

Issue - State: open - Opened by Davinho10 over 1 year ago - 2 comments

#97 - The problem of multi-agent

Issue - State: open - Opened by yx457994451 over 1 year ago - 1 comment

#96 - Display vehicle attention and distribution of actions only works in episode 0

Issue - State: closed - Opened by Karim-SUN over 1 year ago - 1 comment

#95 - gym.error.NameNotFound: Environment intersection doesn't exist.

Issue - State: open - Opened by Lucyliu09 over 1 year ago - 3 comments

#94 - How to config the exploration

Issue - State: open - Opened by qinxianyuzi over 1 year ago - 1 comment

#93 - Analyze.py file missing?

Issue - State: open - Opened by Davinho10 almost 2 years ago - 1 comment

#92 - some implementation issues

Issue - State: open - Opened by 6Lackiu almost 2 years ago - 14 comments

#91 - ModuleNotFoundError: No module named 'finite_mdp'

Issue - State: open - Opened by zsn2021 almost 2 years ago - 3 comments

#90 - Log: agent statistics

Issue - State: closed - Opened by siddahant almost 2 years ago - 3 comments

#89 - TypeError: must be real number, not dict while running highway env with dqn

Issue - State: closed - Opened by siddahant almost 2 years ago - 5 comments

#88 - Recommended gym and highway-env versions

Issue - State: closed - Opened by ShirelJosef about 2 years ago - 3 comments

#87 - display of env 'IntersectionEnv':

Issue - State: open - Opened by swb19 about 2 years ago - 1 comment

#86 - The script runs DDQN

Issue - State: open - Opened by zhangjianguo-max about 2 years ago - 1 comment

#85 - rl-agent

Pull Request - State: closed - Opened by zhangjianguo-max about 2 years ago - 1 comment

#84 - Issue with deepcopy

Issue - State: open - Opened by jlwu002 over 2 years ago - 4 comments

#83 - `Temperature` variable in Monte Carlo Tree Search

Issue - State: closed - Opened by AndreasKaratzas over 2 years ago - 2 comments

#82 - Fix: finalised monitor deprecation in experiments and evaluation scripts

Pull Request - State: closed - Opened by TibiGG over 2 years ago - 3 comments

#81 - How to change a default network structure?

Issue - State: open - Opened by lucalazzaroni over 2 years ago - 2 comments

#80 - Caching of previous_state non-compatible with Multi-Agent

Issue - State: open - Opened by TibiGG over 2 years ago - 1 comment

#79 - DQN-Social Attention in Highway-env

Issue - State: open - Opened by SimoMaestri over 2 years ago - 5 comments

#78 - ImportError: cannot import name 'RecordVideo'

Issue - State: closed - Opened by skonwa over 2 years ago - 2 comments

#77 - the instance command failed

Issue - State: closed - Opened by yuzhouxianzhi over 2 years ago - 1 comment

#76 - the instance command failed

Issue - State: closed - Opened by yuzhouxianzhi over 2 years ago

#75 - Possible issue about the module named 'rl_agents.agents.tree_search.robust'

Issue - State: closed - Opened by JasonWong815 almost 3 years ago - 2 comments

#74 - cannot pickle '_thread.lock' object

Issue - State: closed - Opened by bosunrunner about 3 years ago - 2 comments

#72 - Implementing Convolutinal DQN Network from the scripts

Issue - State: closed - Opened by OscarHuangWind over 3 years ago - 4 comments

#71 - Egoattention does not work in other scenario

Issue - State: closed - Opened by Yabing67 over 3 years ago - 1 comment

#70 - Prioritized Experience Replay

Issue - State: open - Opened by skynox03 over 3 years ago - 2 comments

#69 - How do I save a trained model to reuse it?

Issue - State: open - Opened by shivambhandari99 over 3 years ago - 3 comments

#65 - [Question] Rationale behind visualization of confidence ellipses

Issue - State: closed - Opened by GPrathap over 3 years ago - 4 comments

#64 - Model Weights and Biases - Histogram Tensorboard

Issue - State: closed - Opened by skynox03 over 3 years ago - 4 comments

#63 - analyze agent performances

Issue - State: closed - Opened by denghuifan over 3 years ago - 4 comments

#62 - Logging Error

Issue - State: closed - Opened by skynox03 almost 4 years ago - 1 comment

#61 - Modify the comment for OPD.

Pull Request - State: closed - Opened by KexianShen almost 4 years ago - 1 comment

#60 - Some questions about ego attention DQN

Issue - State: closed - Opened by Exasor almost 4 years ago - 2 comments

#59 - mcts.py: fix child prior regularization update

Pull Request - State: closed - Opened by sritee almost 4 years ago - 1 comment

#58 - recorded mp4 format video cannot play

Issue - State: closed - Opened by JianmingTONG almost 4 years ago - 5 comments

#57 - Can't find cartpole_benchmark.json

Issue - State: closed - Opened by jackliu333 almost 4 years ago - 1 comment

#56 - how to run more episodes?

Issue - State: open - Opened by SHITIANYU-hue almost 4 years ago - 1 comment

#55 - Can't import rl_agents in Python 3.7.1

Issue - State: open - Opened by davidwitten almost 4 years ago - 1 comment

#54 - [Minor] Typo in readme

Pull Request - State: closed - Opened by davidwitten almost 4 years ago - 1 comment

#53 - Minor fix for benchmark_agents.json of CartPole env

Pull Request - State: closed - Opened by ashishrana160796 about 4 years ago - 1 comment

#52 - rl-agents compatible with continuous action spaces

Issue - State: open - Opened by SHITIANYU-hue about 4 years ago - 3 comments

#51 - Vehicle type changed in safe_deepcopy_env()

Issue - State: open - Opened by rongliangzi about 4 years ago - 5 comments

#50 - Gridworld scenario running issues

Issue - State: open - Opened by hebowei2000 about 4 years ago - 2 comments

#49 - Bug fix

Pull Request - State: closed - Opened by saArbabi about 4 years ago - 2 comments

#48 - Minor bug fix

Pull Request - State: closed - Opened by saArbabi about 4 years ago

#47 - Questions about MCTS

Issue - State: closed - Opened by marooncn about 4 years ago - 13 comments

#46 - Questions about selection_rule in OPD

Issue - State: closed - Opened by marooncn about 4 years ago - 1 comment

#45 - mcts with dpw

Pull Request - State: closed - Opened by saArbabi over 4 years ago - 3 comments

#44 - stochastic transitions for tree search agents

Issue - State: closed - Opened by saArbabi over 4 years ago - 2 comments

#44 - stochastic transitions for tree search agents

Issue - State: closed - Opened by saArbabi over 4 years ago - 2 comments

#43 - Flawed Management of internal search environments in tree search planning

Issue - State: closed - Opened by amarildolikmeta over 4 years ago - 8 comments

#41 - How to contribute?

Issue - State: open - Opened by mhtb32 over 4 years ago - 2 comments

#40 - how to test the training data

Issue - State: closed - Opened by Wasedarocket over 4 years ago - 2 comments

#39 - IndexError: tuple index out of range

Issue - State: open - Opened by Pei-w over 4 years ago - 2 comments

#38 - How to analyze the data after being successfully trained.

Issue - State: closed - Opened by zhaoworking over 4 years ago - 13 comments

#37 - Analyze Data

Issue - State: closed - Opened by mkapron9 over 4 years ago - 9 comments

#36 - Possible issue about the robust value iteration

Issue - State: open - Opened by DanialTaheri over 4 years ago - 1 comment

#35 - Questions from the entrant

Issue - State: closed - Opened by Pei-w over 4 years ago - 1 comment

#34 - Hi ！

Issue - State: closed - Opened by CFXgoon over 4 years ago - 56 comments

#31 - How to find the env configure file -- .json file?

Issue - State: closed - Opened by zhaoworking over 4 years ago

#30 - Hi，the problem of the reward function.

Issue - State: closed - Opened by zhangxinchen123 over 4 years ago - 3 comments

#29 - hello，I am a beginner in the reinforcement learning！！

Issue - State: closed - Opened by zhangxinchen123 over 4 years ago - 6 comments

#28 - Add receding horizon mechanism

Pull Request - State: closed - Opened by p-shg almost 5 years ago

#27 - Adding visualisation of the tree

Pull Request - State: closed - Opened by p-shg almost 5 years ago

#26 - Better logger for OPD

Pull Request - State: closed - Opened by p-shg almost 5 years ago

#25 - Fix olop mistake

Pull Request - State: closed - Opened by p-shg almost 5 years ago - 1 comment

#24 - DeterministicPlannerAgent checkpoint saving error

Issue - State: closed - Opened by songanz almost 5 years ago - 1 comment

#23 - ImportError: No module named 'rl_agents.agents.budgeted_ftq'

Issue - State: closed - Opened by autonomobil about 5 years ago - 3 comments

#22 - Add custom env

Issue - State: closed - Opened by arita37 over 5 years ago - 7 comments

#21 - The car cannot perform like the GIF after training converged

Issue - State: closed - Opened by LevineYang over 5 years ago - 6 comments

#20 - Rename UCT and OPD

Issue - State: open - Opened by eleurent over 5 years ago

#19 - Add a pipeline to train agents relying on workers to collect experiences

Issue - State: closed - Opened by eleurent over 5 years ago - 2 comments

#18 - Remove pygame dependency.

Issue - State: open - Opened by eleurent over 5 years ago