├── .gitignore ├── README.md ├── async_agent.py ├── config.py ├── core.py ├── impala.py ├── main.py ├── source ├── entropy.png ├── episode_step.png ├── max_prob.png ├── pi_loss.png ├── score.png ├── value_loss.png └── video.gif ├── utils.py └── vtrace.py /.gitignore: -------------------------------------------------------------------------------- 1 | __pycache__/ 2 | runs/ 3 | nohup.out 4 | save-mov/ 5 | .DS_Store/ 6 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/README.md -------------------------------------------------------------------------------- /async_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/async_agent.py -------------------------------------------------------------------------------- /config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/config.py -------------------------------------------------------------------------------- /core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/core.py -------------------------------------------------------------------------------- /impala.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/impala.py -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/main.py -------------------------------------------------------------------------------- /source/entropy.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/source/entropy.png -------------------------------------------------------------------------------- /source/episode_step.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/source/episode_step.png -------------------------------------------------------------------------------- /source/max_prob.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/source/max_prob.png -------------------------------------------------------------------------------- /source/pi_loss.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/source/pi_loss.png -------------------------------------------------------------------------------- /source/score.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/source/score.png -------------------------------------------------------------------------------- /source/value_loss.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/source/value_loss.png -------------------------------------------------------------------------------- /source/video.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/source/video.gif -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/utils.py -------------------------------------------------------------------------------- /vtrace.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/RLOpensource/IMPALA-Scalable-Distributed-Deep-RL-with-Importance-Weighted-Actor-Learner-Architectures/HEAD/vtrace.py --------------------------------------------------------------------------------