AboudyKreidieh / h-baselines

90%

LAST BUILD ON BRANCH master

branch: master

CHANGE BRANCH

x

Reset

• master
• 0.1.0
• PD-Biped3D-HLC-Soccer-v1
• adds
• ant-four-rooms
• ant-visualizer
• antfall-fix
• antfourrooms-update
• antgather-2
• antgather-update
• av-reward
• av-ring-2
• baselines_cleanup
• benchmarking-description
• benchmarking-results-2
• better-logging
• brandon-merge
• brandon-merge-2
• bug-fixes
• cg-final
• cg-final-2
• cleanup
• cleanup2
• cleanup_2
• connected-gradients
• context_get_action
• dependabot/pip/tensorflow-1.14.0
• dependabot/pip/tensorflow-1.15.0
• dependabot/pip/tensorflow-1.15.2
• dependabot/pip/tensorflow-1.15.4
• docs
• dynamic-lr
• dynamic-lr-2
• dynamir-lr-2
• env-bug-fix
• env-cleanup
• env-update
• eps-greedy
• eval
• experiments-doc
• fast-ring-maddpg
• fingerprint-eval
• fingerprints
• flow-action-update
• flow-env-update
• flow-envs-update
• flow-import
• fs-env
• get-rl-accel
• harder-antmaze
• hierarchical-policy-fn
• hierarchical-replay-buffer
• hierarchical-replay-buffer-2
• hierarchical_replay_buffer
• highway-single
• hindsight
• hindsight_bug_fix
• hiro
• humanoid
• humanoid-envs
• imitation
• imitation-base-policy
• imitation-fcnet
• info-at-done
• l2-penalty
• logdir
• mixed-autonomy
• model-v3
• multi-fcnet
• multi-fcnet-agent
• multi-fcnet-cleanup
• multi-fcnet-get-action
• multi-fcnet-get-td-map
• multi-fcnet-shared-independent
• multi-fcnet-store-transition
• multi-fcnet-value
• multi-goal-conditioned-2
• multi-level-hierarchies
• multi-replay-buffer
• multi_goal_conditioned
• multiagent-fix
• multiagent-fixes
• multiagent-hrl
• multiagent-tests
• multilevel-description
• multilevel-hiro
• multilevel-updates
• multisetp-llp
• mv_algorithm
• mv_policy
• new-worker-reward
• normalized_obs_reward
• np_replay_buffer
• off-policy-corrections
• onpolicy-policy
• open-multiagent
• ou_noise
• parallel-steps
• parallel-steps-3
• parsing_augmentations
• phi-t
• plotter
• point2d-bipedal-envs
• policy-restructure
• policy_abstractions
• policy_kwargs
• ppo
• ppo2
• ppo3
• pretrain-multilevel
• pull-request-template
• ray-sampler
• readme
• readme-update
• remaining-td3-features
• ring-env-0
• ring-env-merge
• ring-fast-all
• rl_algorithm
• run_eval
• sac
• sac-hiro
• sac2
• sampler
• savio
• seeds_feature_cleanup
• snake-gather
• speedup
• subgoal-testing
• swimmer-gather
• target_policy_noise
• td3
• tensorboard
• test_runner_scripts
• tests
• todo-fixme
• universal_buffer
• updated_env
• updated_policy_algorithm
• variable-inflows
• working-hac-envs
• working-hiro
• working_baselines

Updated README + tests (#254)