MarathonEnvs-v3.0.0

What's new in MarathonEnvs-v3.0.0

New Controller Environments (Preview)

• ControllerMarathonMan-v0 - Uses the new ArticulatedBody joint type which was introduced in Unity 2020.1

Unity 2020.1 Beta

• Updated to use Unity 2020.1 Beta 12.

MarathonEnvs-v2.0.0

What's new in MarathonEnvs-v2.0.0

New Style Transfer Environments

• MarathonManWalking-v0
• MarathonManRunning-v0
• MarathonManJazzDancing-v0
• MarathonManMMAKick-v0
• MarathonManPunchingBag-v0
• MarathonManBackflip-v0
• Plus various fixes to improve performance and make it closer to DeepMimic paper.

Guide to Working With Style Transfer

• Guide on how to train your custom motion capture sequence.

WebGL Demo / Support for in browser

• See Web Demo

marathon-envs Gym wrapper (Preview)

• Use marathon-envs as a OpenAI Gym environment - see documentation

ml-agents 0.14.1 support

• Updated to work with ml-agents 0.14.1 / new inference engine

Unity 2018.4 LTS

• Updated to use Unity 2018.4 LTS. Should work with later versions. However, sometimes Unity makes breaking physics changes.

MarathonManBackflip-v0

• Train the agent to complete a backflip based on motion capture data
• Merged from StyleTransfer experimental repro

MarathonMan-v0

• Optimized for Unity3d + fixes some bugs with the DeepMind.xml version
• Merged from StyleTransfer experimental repro
• Replaces DeepMindHumanoid

ManathonManSparse-v0

• Sparse version of MarathonMan.
• Single reward is given at end of the episode.

TerrainHopperEnv-v0, TerrainWalker2dEnv-v0, TerrainAntEnv-v0, TerrainMarathonManEnv-v0

• Random Terrain environments
• Merged from AssaultCourse experimental repro

SpawnableEnvs (Preview)

• Set the number of instances of an environment you want for training and inference
• Environments are spawned from prefabs, so no need to manually duplicate
• Supports ability to select from multiple agents in one build
• Unique Physics Scene per Environment (makes it easier to port environments however runs slower)
• SelectEnvToSpawn.cs - Optional menu to enable user to select from all agents in build

Scorer.cs

• Score agent against 'goal' (for example, max distance) to distinguish rewards from goals
• Gives mean and std-div over 100 agents

Normalized Observations (-1 to 1) and reward (0 to 1)

• No need to use normalize flag in training. Helps with OpenAI.Baselines training

Merge CameraHelper.cs from StyleTransfer. Controls are

• 1, 2, 3 - Slow-mo modes
• arrow keys or w-a-s-d rotate around agent
• q-e zoom in / out

Default hyperparams are now closer to OpenAI.Baselines

• (1m steps for hopper, walker, ant, 10m for humanoid)

Training speed improvements - All feet detect distance from floor

MarathonEnvs-v2.0.0-alpha.2

Fixes issues with OpenAI Gym wrapper - updated binaries

MarathonEnvs v2.0.0-alpha.1

What's new in MarathonEnvs-v2.0.0-alpha.1

WebGL Demo / Support for in browser

• See Web Demo

marathon-envs Gym wrapper (Preview)

• Use marathon-envs as a OpenAI Gym environment - see documentation

ml-agents 0.14.1 support

• Updated to work with ml-agents 0.14.1 / new inference engine

Unity 2018.4 LTS

• Updated to use Unity 2018.4 LTS. Should work with later versions. However, sometimes Unity makes breaking physics changes.

MarathonManBackflip-v0

• Train the agent to complete a backflip based on motion capture data
• Merged from StyleTransfer experimental repro

MarathonMan-v0

• Optimized for Unity3d + fixes some bugs with the DeepMind.xml version
• Merged from StyleTransfer experimental repro
• Replaces DeepMindHumanoid

ManathonManSparse-v0

• Sparse version of MarathonMan.
• Single reward is given at end of episode.

TerrainHopperEnv-v0, TerrainWalker2dEnv-v0, TerrainAntEnv-v0, TerrainMarathonManEnv-v0

• Random Terrain envionments
• Merged from AssaultCourse experimental repro

SpawnableEnvs (Preview)

• Set the number of instances of an envrionmwnt you want for training and inference
• Envrionments are spawned from prefabs, so no need to manually duplicate
• Supports ability to select from multiple agents in one build
• Unique Physics Scene per Environment (makes it easier to port envionments however runs slower)
• SelectEnvToSpawn.cs - Optional menu to enable user to select from all agents in build

Scorer.cs

• Score agent against 'goal' (for example, max distance) to distinguish rewards from goals
• Gives mean and std-div over 100 agents

Normalized Observations (-1 to 1) and reward (0 to 1)

• No need to use normalize flag in training. Helps with OpenAI.Baselines training

Merge CameraHelper.cs from StyleTransfer. Controls are

• 1, 2, 3 - Slow-mo modes
• arrow keys or w-a-s-d rotate around agent
• q-e zoom in / out

Default hyperparams are now closer to OpenAI.Baselines

• (1m steps for hopper, walker, ant, 10m for humanoid)

Training speed improvements - All feet detect distance from floor

MarathonEnvs 0.5.0a

Requires: ML-Agents Beta 0.5.0a or download the Quick Start zip which includes

• marathon-envs-0.5.0a
• ml-agents-0.5-3.0a
• TensorFlowSharp

MarathonEnvs 0.5.0

Requires ML-Agents Beta 0.5.0