Skip to content
Snippets Groups Projects
Select Git revision
  • 150_render_graph_d3js
  • 170_save_episode
  • 170_save_episode_b
  • 178-bug-in-step-function-reported-vetrov_andrew
  • 223-update-editor
  • 223_UpdateEditor_55_notebooks
  • 242-distance-map-performance-speed-up
  • 245-bug-distance-map-cacluation
  • 249-evaluator-bug-service-py-client-py
  • 249-evaluator-bug-service-py-client-py-2
  • 250-tests-for-agent-static
  • 263_malfunction_last_step
  • 264_fixing_examples
  • 264_revisited
  • 271-add-agent-index-to-global-agent-position-matrix
  • 273_malfunction_loading_and_saving
  • 308_fix
  • 323_unordered_cell_locking
  • 323_unordered_cell_locking_no_graphviz
  • 325_eval_step_timeout
  • generator_persistence_tag
  • v2.2.1
  • v2.2.0
  • v2.1.10
  • v2.1.9
  • v2.1.8
  • v2.1.7
  • v2.1.6
  • v2.1.5
  • v2.1.4
  • v2.1.3
  • v2.1.2
  • v2.1.1
  • v2.1.0
  • v2.0.0
  • v0.3.10
  • v0.3.9
  • v0.3.8
  • v0.3.7
  • v0.3.6
40 results
You can move around the graph by using the arrow keys.
Created with Raphaël 2.2.08Jun75432323231May24201918121110730Apr2524121013Mar42124Jan18131110763230Dec2928212017141364230Nov29282726252221201914131211876542131Oct30292827252423222118171614131211109876543Bumped version to 2.2.0v2.2.0v2.2.0Updated READMEMerge remote-tracking branch 'origin/master'Updated READMEMerge branch 'fix_malfunction_prob' into 'master'Merge branch 'master' of gitlab.aicrowd.com:flatland/flatlandupdated editor to work with persistence. Modified test rail_env / single_agent and re-enabled. Added test_env_loop.pkl to go with the test.Fixed tests following malfunction rate fixfix_malfunction…fix_malfunction_probFixed malfunction probabilityMerge branch 'spm/321-group-rewards-in-evaluation-service' into 'master'use default None for results output path in clispm/321-group-r…spm/321-group-rewards-in-evaluation-serviceRefactor reward computationsUpload metadata csv file to S3 when applicableMerge branch 'spm/321-group-rewards-in-evaluation-service' into 'master'Addresses #321 - Groups the rewards across test_ids in the evaluation serviceMake metadata.csv mandatory for evaluation serviceDisabled flake8 in toxPinned PyVirtualDisplay version even lowerMerge remote-tracking branch 'origin/master'Pinned PyVirtualDisplay version to avoid bug with pytest-xvfb (https://github.com/The-Compiler/pytest-xvfb/issues/22)updated import for random_rail_generator in Simple_Rendering_Demo.ipynbin editor.py update the import of random_rail_generator from rail_env to rail_generatorsremoved instances of typing from rail_env.py which were causing problems with cyclic importsswitched a shortest_path test back to loading from a package resource rather than a file pathchanged the assertRaises to check for ValueError rather than SystemExit when cities cannot be packed inadded some debug (now commented) looking into the shortest path failures. Now apparently identified / resolved.removed some commented code, commented a print, schedule_generators.pymoved the agents_static legacy logic, and the tuple to EnvAgent conversion, into the load_env_dictadded some debug (commented) to test_rail_env_single_agent, and set the test to skipset show=False in render_env call from test to avoid native window openingcatch endless loops in rain_env testfix msgpack version to 0.6.1 - same as rllib. encoding arg.switched back to load_resource in rail_env test. passed load_from_package arg down to from_file generators. switch default renderer to PGL from BROWSER. Added conditional import for flask_util in rendertools to hopefully avoid some startup delays and hanging tests. Added os.makedirs to intro_flatland 2.1 for saved frames folder. Removed explicit gl=PILSVGFix persistence testsspm/fix_testsspm/fix_testsMerge branch 'spm/318-finegrained-metrics' into 'master'Print evaluation_metric_df only if the evaluator is running in verbose modespm/318-finegra…spm/318-finegrained-metricsAdd controller inference times to fine grained evaluation metricsPass controller inference time from client to serverAdd pandas dependency to requirementsAdd more finegrained metrics to client and service