v0.2.0

CHANGELOG

@@ -1,3 +1,44 @@
+2021.9.30(v0.2.0)
+- env: overcooked env (#20)
+- env: procgen env (#26)
+- env: modified predator env (#30)
+- env: d4rl env (#37)
+- env: imagenet dataset (#27)
+- env: bsuite env (#58)
+- env: move atari_py to ale-py
+- algo: SQIL algorithm (#25) (#44)
+- algo: CQL algorithm (discrete/continuous) (#37) (#68)
+- algo: MAPPO algorithm (#62)
+- algo: WQMIX algorithm (#24)
+- algo: D4PG algorithm (#76)
+- algo: update multi discrete policy(dqn, ppo, rainbow) (#51) (#72)
+- feature: image classification training pipeline (#27)
+- feature: add force_reproducibility option in subprocess env manager
+- feature: add/delete/restart replicas via cli for k8s
+- feautre: add league metric (trueskill and elo) (#22)
+- feature: add tb in naive buffer and modify tb in advanced buffer (#39)
+- feature: add k8s launcher and di-orchestrator launcher, add related unittest (#45) (#49)
+- feature: add hyper-parameter scheduler module (#38)
+- feautre: add plot function (#59)
+- fix: acer bug and update atari result (#21)
+- fix: mappo nan bug and dict obs cannot unsqueeze bug (#54)
+- fix: r2d2 hidden state and obs arange bug (#36) (#52)
+- fix: ppo bug when use dual_clip and adv > 0
+- fix: qmix double_q hidden state bug
+- fix: spawn context problem in interaction unittest (#69)
+- fix: formatted config no eval bug (#53)
+- fix: the catch statments that will never succeed and system proxy bug (#71) (#79)
+- fix: lunarlander config
+- fix: c51 head dimension mismatch bug
+- fix: mujoco config typo bug
+- fix: ppg atari config bug
+- fix: max use and priority update special branch bug in advanced_buffer
+- style: add docker deploy in github workflow (#70) (#78) (#80)
+- style: support PyTorch 1.9.0
+- style: add algo/env list in README
+- style: rename advanced_buffer register name to advanced
+
+
 2021.8.3(v0.1.1)
 - env: selfplay/league demo (#12)
 - env: pybullet env (#16)

README.md

@@ -31,7 +31,7 @@
 [![Contributors](https://img.shields.io/github/contributors/opendilab/DI-engine)](https://github.com/opendilab/DI-engine/graphs/contributors)
 [![GitHub license](https://img.shields.io/github/license/opendilab/DI-engine)](https://github.com/opendilab/DI-engine/blob/master/LICENSE)
 
-Updated on 2021.08.03 DI-engine-v0.1.1 (beta)
+Updated on 2021.09.30 DI-engine-v0.2.0 (beta)
 
 
 ## Introduction to DI-engine (beta)

ding/__init__.py

@@ -1,7 +1,7 @@
 import os
 
 __TITLE__ = 'DI-engine'
-__VERSION__ = 'v0.1.1'
+__VERSION__ = 'v0.2.0'
 __DESCRIPTION__ = 'Decision AI Engine'
 __AUTHOR__ = "OpenDILab Contributors"
 __AUTHOR_EMAIL__ = "[email protected]"

ding/entry/tests/test_serial_entry.py

@@ -367,7 +367,7 @@ def test_d4pg():
     except Exception:
         assert False, "pipeline fail"
 
-        
+
 def test_discrete_cql():
     # train expert
     config = [deepcopy(cartpole_qrdqn_config), deepcopy(cartpole_qrdqn_create_config)]
@@ -395,4 +395,4 @@ def test_discrete_cql():
     except Exception:
         assert False, "pipeline fail"
     finally:
-        os.popen('rm -rf cartpole cartpole_cql')
+        os.popen('rm -rf cartpole cartpole_cql')

ding/policy/command_mode_policy_instance.py

@@ -200,6 +200,7 @@ class ACERCommandModePolisy(ACERPolicy, DummyCommandModePolicy):
 class QTRANCommandModePolicy(QTRANPolicy, EpsCommandModePolicy):
     pass
 
+
 @POLICY_REGISTRY.register('d4pg_command')
 class D4PGCommandModePolicy(D4PGPolicy, DummyCommandModePolicy):
-    pass
+    pass

setup.py

@@ -117,12 +117,12 @@
         'minigrid_env': [
             'gym-minigrid',
         ],
-        'd4rl_env': [
-            'd4rl @ git+https://github.com/rail-berkeley/d4rl@master#egg=d4rl',
-        ],
-        'pybulletgym_env': [
-            'pybulletgym @ git+https://github.com/benelot/pybullet-gym@master#egg=pybulletgym',
-        ],
+        # 'd4rl_env': [
+        #     'd4rl @ git+https://github.com/rail-berkeley/d4rl@master#egg=d4rl',
+        # ],
+        # 'pybulletgym_env': [
+        #     'pybulletgym @ git+https://github.com/benelot/pybullet-gym@master#egg=pybulletgym',
+        # ],
         'sc2_env': [
             'absl-py>=0.1.0',
             'future',